ABSTRACT

All industries and stores has workers for turmeric size segregation but
recognizing, categorizing and ranking of turmeric sizes are not done correctly.
As categorizing is one of the most important industry provocations, a
dependable categorizing method is needed so it would be secure to pack
automatically. So, it is required to inflict the hardware system in turmeric size
industry. In accordance with the need of hardware segmenting and packaging
system for turmeric sizes in the supermarket and the limitation of current
methods, this project proposes a new segregation method for turmeric sizes for
packing. Under natural lighting conditions the turmeric sizes are segregated.
To segment images of turmeric sizes we use machine learning techniques. In
order to find a turmeric size in each image and to determine its location twenty
digitized images of turmeric sizes were randomly selected. We compared the
results of both segmentation results and the size based segmentation
outperforms the edge-based segmentation in all aspects. With the adequate
concepts of image processing there is a great scope to provide intelligence for
designing on automation system to differentiate the turmeric sizes according to
its size. This process will lead to developing a product that will segregate all
turmeric size in industries and even in grocery stores. A Microcontroller is
used to drive the sorted turmeric sizes as per the need to their allotted buckets.
Implementation of all segmentation methods on turmeric size images is
applied and a comparative outcome is projected
 LIST OF ABBREVIATIONS

ABBREVIATIONS EXPANSIONS
IMAGE PROCESSING Turmeric segregation
RCV Remote Control Vehicle
AC Alternating Current
USB Universal Serial Bus
IDE Integrated Development Environment
ICSP In Circuit Serial Programming
DC Direct Current
IR Infra Red
IORef Input Output Reference

KB Kilo Byte
SRAM Static Random Access Memory
EEPROM Electrically Erasable Programmable Read
Only Memory
LED Light Emitting Diode
GND Image processingund
TTL Transistor-Transistor Logic
PAN Personal Area Network
FHSS Frequency-Hopping Spread Spectra
EN Enable
RM Relative Moisture
AM Absolute Moisture
TCP Transmission Control Protocol
IP Internet Protocol
 LIST OF FIGURES

FIGUR NAME OF THE FIGURE

E NO.
2.1 Existing system
3.1 Waterfall model
4.10 Inductive proximity sensor
4.11 USB web camera
4.12 12V DC motor
4.13 ZIGBEE wifi module
4.14 ATmega8 IDE
4.15 Front view of the Smart trash and dust
collection-segregation robot
4.16 Top view of the Smart robot
5.1 Distance vs Response time
5.2 Screenshot of the app
5.3 Level of the garbage using RFID scanner
5.4 Structure of robotic arm
 CHAPTER 1
INTRODUCTION

1.1 INTRODUCTION

This overall system is based on the MATLAB software and consists of hardware too.
The Image is being processed by using MATLAB software whenever the turmeric
size is detected. Hardware consist of microcontroller and motors. The servo motor
pass the turmeric sizes and packaging boxes at specified time and these are run by
drivers by the command of microcontroller. This system automates the process of
turmeric size sorting and packaging. The turmeric sizes are passed one by one which
is sensed and image is captured and image processing is done by MATLAB software
and thus spot detection is done. Finally we get the result whether the turmeric size is
accepted or rejected. The turmeric size is collected in it and if the turmeric size is
rejected then the turmeric size is moved to the other side with the help of grip. This
leads to the ease at meeting the requirement of customer and their satisfaction.
Because at the end any industry would aim to meet their customer need and to look
after their requirements. In Texture method, when an element or pattern on a surface
that is repeated on a regular basis, it is called as Texture. The most crucial attribute is
texture in many image analysis and computer vision analysis. The procedures are
further divided into constructive approach, design based approach, analytical
approach and refine based approach. 1.2 History Various algorithms for texture
feature analysis have been proposed by researchers, such as the Wavelet
decomposition method. The extended method is typically based on the cooccurrence
matrix to describe the image features with gradient operator. The texture features are
extracted according to grey level co-occurrence matrix and grey level run-length
matrix. The images obtained from the colour CCD video camera are changed
considering different consumer may pack and place in their own way even if under
the same illumination condition. So, our algorithm should have good robustness in
order to solve the problem. Apart from these, some turmeric sizes have extremely
similar colour, such as guava and green turmerics, white pears and white turmerics.
1.2 BACKIMAGE PROCESSINGUND

Overall, many problems remain to be solved to enable the automatic weighing and
pricing system to recognize turmeric sizes precisely. With the unique development of
this method with grey-scale images, it has been an extensively efficient form,
applicable to colour images. Conventional edge based techniques usually form
disjointed borders that calls for post-processing for producing congested regions. The
borders of the resultant regions constantly match up to contours appearing in the
image as evident contours of objects. The combination of the entire region forms the
complete image area. After segmentation the MATLAB output will be sent to the
Microcontroller.
Here we have used an ATmega8 Microcontroller which helps for packing.
The turmeric sizes packed into three packing buckets. If the recognized
turmeric size is a selected type Microcontroller will send it to second packing
bucket. When the recognised turmeric sizes are very small in size then it will
send the first packing bucket. Or if the segmented turmeric sizes are bigger
than the selected size then the microcontroller will send it to the third packing
bucket. Here, we have used an ATmega8 microcontroller and stepper motor
for the packing process

1.3 OBJECTIVE

Fresh turmeric size harvesting can be done by using the digitized images of turmeric
sizes that were randomly selected from the Internet and all the images would be of
different pixel size. The images will be captured at different lighting conditions with
different background sizes and different camera positions. All of this images will be
sent to the MATLAB as input image. The MATLAB helps recognize the selected
image with the help of image segmentation process. In our proposed system the
image segmentation is based on colour of the selected turmeric size and edge based
segmentation. The segmented imaged recognized by MATLAB will be sent to the
Microcontroller. The Microcontroller ATmega8 used here help to packing of
turmeric sizes.
1.4 PROBLEM STATEMENT

Manual harvesting may be a traditional and customary method to reap turmeric

sizes. Even though that's a labour intensive, manual harvesting is quite common for
turmeric sizes that have huge for optimal maturity or for turmeric sizes that are
marketed for direct consumption for the people. Historically, manual harvesting has
been the well-liked method for achieving high-quality control and minimizing tree
damage. Also, manual harvesting is usually administered as a clean-up operation
either after the mechanical harvesting or at the top of the harvesting season to select
up the turmeric sizes that are left behind. the popularity of turmeric sizes and packing
are done by humans. Fresh produce sold through markets or by direct sales to users
or agents would undergo some sorting and packaging. This method involves packing
of turmeric sizes by hand, using plastic wraps and plastic foam containers etc.
Properly trained workers segregate, pack and handle the turmeric sizes with
minimum damage. The packed turmeric sizes are placed in big cardboard boxes of
various sizes, depending upon the dimensions of turmeric size. The labours are
expected to wear clean aprons, gloves and head covers. The stamina needed to
segregate turmeric sizes from the load is typically higher and any less of required
stamina may end in diminished packing rates. Manual picking and packing could
also be done either by hand or using semi-manual tools that are heavy for prolonged
handling. The turmeric sizes which will easily be damaged while handling like
peaches, cherries, bananas, etc. should be packed by handling the turmeric size
firmly and gently, and punctiliously.
 CHAPTER 2
LITERATURE SURVEY
2.1 LITERATURE SURVEY

In [4] they used an ATMEGA8, as well as an ultrasonic sensor, a servo motor, and a
battery jumper cable, to create a smart Turmeric size segregation. In [1] they suggest
Image Processing-based Turmeric segregation, as well as a sensor device that will
detect the amount of Turmeric substances in it and send a warning to the municipal
office. In [10] since there is no interaction with thesegregation model, the automatic
door opening mechanism confirms that human garbage disposal is fully hands-free
and therefore very hygienic. Turmeric is separated into categories based on its
capacitance. Wet Turmeric has a slightly higher capacitance than dry Turmeric and
plastic, making it readily distinguishable. Some dry Turmeric has different reflective
properties than plastic, and as a result, the best method for distinguishing plastic
from other dry Turmeric is infrared spectroscopy.
In[8] they mostly focused on Hospital automation systems (which can also be used in
malls and other public places) and hope that this can be applied on a wide scale in
the future. The Turmerics are separated into categories so that they can be easily
disposed of according to their form. In addition, the Turmeric information is
submitted directly to a cloud database in real time. As a result, the Smart Garbage
Segregation & Management System would assist in garbage disposal by segregating
it according to its form, thereby contributing to society and the environment in a
green manner. In [6] they introduced an Turmeric segregation (Image Processing)
framework that not only sends a warning to the company about the overflow and
toxicity level of the Turmeric Size segregations, but also creates a website to track
the data related to the Turmeric Size segregations.

The message is sent to the mobile phone via module, and data about the Turmeric
Size segregation status is updated on the website. People may also file concerns
about trash cans or Turmeric management on this website. The ATmega8 is used as a
microcontroller in the recommended framework to communicate between the LCD
module and the IR sensors, which are used to determine level and toxicity,
respectively.
In [3], The basic idea is to introduce a smart way of handling garbage by using the
IMAGE PROCESSING protocol to wirelessly relay Turmeric Size segregation status
to the concerned individual via e-mail to inform them that the device is full of
garbage and needs to be replaced. In [5] they've taken a more cost-effective
approach to Turmeric management. Furthermore, the matter of Turmeric spilling
due to overcrowding of trucks has been resolved.

In [7] they suggested a topic on Turmeric management focused on the current issues
that it is creating. This was exacerbated by irresponsible Turmeric management, and
as a result, it has been reported that it has a negative impact over time. Turmeric
management is recommended not only for the common solution of a sanitary climate,
but also for other economic, social, environmental, and intergenerational benefits.
The study was expected due to their country's condition, in which it is required to
segregate Turmeric into wet and dry categories. But, due to a lack of time, Turmeric
is usually segregated without much thought; however, a suggested solution is to
establish automated Turmeric segregation using a moisture sensor. The sensor senses
whether the Turmeric is wet or dry and separates it accordingly. Furthermore,
ultrasonic sensors detect the wet and dry Turmeric segregation models, determining
if they are full or not, and if so, how full they are.

In [2] they defined how Solar Smart segregation model can be used to handle an
entire city's Turmeric collection system. In [9] they suggested an Image Processing-
based smart Turmeric management system that uses sensor systems to control the
Turmeric level in thesegregation models. As soon as it was detected, the device was
changed to concern approved via GSM/GPRS.

2.2 EXISTING SYSTEM

In the existing system garbage is collected by corporation by weekly once or by 2

days once. Though the garbage shrinks and overflows the garbagesegregation model
and spread over the roads and pollutes the environment. The smell will be heavy and
produces air pollution and spreads disease. The street dogs and animals eat the
Turmeric food and spreads over the area and creates dirty environment to avoid such
situation we are planning to design image processing Based Garbage Management
For Smart Cities.

2.3 PROPOSED SYSTEM

The system is more user-friendly and easier to operate. The model is designed such
that anybody can access the machine without the need for basic knowledge. This can
be used to separate metals, plastics, paper, wood, glass Turmeric materials. Then
with the help of a camera and the IMAGE PROCESSING method, the Turmeric can
be identified accordingly and can be separated. The model required Turmeric
materials as inputs and detects them which are further separated. The Turmeric
materials are carried by a conveyor belt which takes the Turmeric materials through
each sensor and finally through the camera. The outcome of this project is the
Turmeric materials which are separated into their respective categories. The inputs
are sent through a conveyor belt which consists of a sensor and a camera. It identifies
the Turmeric materials and gives the output. With the help of the camera module, the
Turmeric material is detected and can be separated into its respective segregation
models. By this, we get the separated Turmeric materials in their respective
segregation models.. The picked-up trash is segregated (metallic and non-metallic,
wet and dry Turmeric) and dumped into the segregation model attached to the robot
which has separate partitions for metallic wet, non-metallic wet, metallic dry and
non-metallic dry trashes. Along with this we have attached a dust collector at the
bottom of the collector bin model which collects minute dust particles like (hair,
sand, dead bugs, etc). Also, we have used image processing for identifying the
objects using IMAGE PROCESSING by camera module.

2.3.1 ADVANTAGES

 Deployment of Turmeric Size segregation based on the actual needs.

 Cost Reduction and resource .
 Improves Environment quality -Fewer smells - Cleaner cities.
 Effective usage of Turmeric Size segregations.
 Dust collector which collects minute dusts.
 Segregation of Turmeric.
 Robotic arm.

2.4 EXPLANATION

Machine learning is a branch of artificial intelligence (AI) and computer science. It

focuses on utilizing data and algorithms to mimic human learning and improve
accuracy over time. This field is closely related to data science and plays a vital role
in extracting valuable insights from data mining projects. By training algorithms with
statistical methods, machine learning enables the generation of classifications and
predictions that can influence decision-making processes in applications and
businesses. The demand for data scientists is expected to rise as big data continues to
expand, as they will be instrumental in identifying crucial business questions and
finding the relevant data to address them. Machine learning is still considered critical
for the advancement of AI, despite its shortcomings. However, ensuring its success
entails adopting a different approach that overcomes its weaknesses, such as the
"black box" problem in unsupervised learning. One such alternative is symbolic
artificial intelligence, which relies on a rule-based methodology for processing data.
In this approach, a knowledge graph is used to define concepts and semantic
relationships, providing transparency and interpretability. By combining machine
learning with symbolic AI, a hybrid AI approach emerges, enabling AI systems to
understand language, not just raw data. This powerful approach revolutionizes data
utilization across various industries by offering deeper insights into what has been
learned and why. For instance, in Turmeric management, our model follows deep
learning algorithms to train the machine using specific Turmeric image features like
shape and size. Once learned, the machine can identify various classes of Turmeric
by recognizing objects resembling them in the images.

Image Processing
Image processing is a crucial process that involves converting an image into digital
form and applying various operations to extract useful information from it. This field
treats images as 2D signals and employs specific signal processing methods to
analyze them. It aims to enhance images or extract relevant information, such as
characteristics or properties associated with the image.

Over time, image processing has emerged as a rapidly developing technology,

occupying a significant research area within engineering and computer science
disciplines. Image processing can be broken down into three fundamental steps.
Firstly, the process begins with the import of the image using specialized image
acquisition tools. Secondly, the image undergoes analysis and manipulation to extract
relevant information or enhance its visual quality. Lastly, the output of the image
processing can take the form of an altered image or a comprehensive report based on
the analysis conducted. Image processing utilizes two primary methods: analog and
digital image processing. Analog image processing is employed for hard copies like
prints and photographs. Image analysts employ various visualtechniques and
interpretations in this context. On the other hand, digital image processing techniques
leverage computer systems to manipulate digital images. When utilizing digital
technology, all types of data typically undergo three general stages: pre-processing,
which involves preparing the data for further analysis; enhancement and display,
where techniques are applied to improve the visual quality of the image; and
information extraction, which involves extracting relevant information or features
from the processed image.

CNN machine learning

Deep learning utilizes CNN machine learning s (IMAGE PROCESSINGs or s),
which are a type of artificial neural network (ANN) primarily used for analyzing
visual imagery. IMAGE PROCESSINGs are also referred to as Shift Invariant or
Space Invariant Artificial Neura l Networks (SIANNs) due to their shared-weight
architecture of kernels or filters. These kernels slide along input features, generating
translation-equivariant responses called feature maps. IMAGE PROCESSINGs find
wide applications in various domains such as image and video recognition,
recommender systems, image classification, image segmentation, medical image
analysis, natural image processing, brain-computer interfaces, and analyzing
financial time series data. CNN machine learning s (IMAGE PROCESSINGs) are
specialized for processing grid-like data like images. They automatically learn
hierarchical representations using al, pooling, and fully connected layers.

IMAGE PROCESSINGs excel at tasks such as image classification, object detection,

and medical image analysis. Their ability to learn features from raw data has led to
breakthroughs in computer vision and other fields.

Turmeric Classification Working

For Turmeric classification using deep learning, a sequential model with five layers
was implemented. Max pooling with a stride of 2 and activation functions like ReLU
and sigmoid were utilized. The number of kernels increased progressively (16, 32,
48, 64) to extract more features from the images. The model was built using the
simplicity of the sequential model in Keras. After and pooling, the output was
flattened to a single vector, preserving spatial structure. The ReLU activation
function ensured linearity, and pooling reduced complexity without sacrificing
performance. The fully connected layer had hidden and output layers, with a softmax
layer added for multi-class classification. The softmax function helped identify the
class of a given Turmeric image in litter classification tasks. Then the model was
compiled using adam optimizer which is a stochastic gradient algorithm and the loss
was given as categorical cross entropy since the problem comprised more than 2
categories. The performance metric was assigned with accuracy. Then the CNN
machine learning model was fitted to the dataset for it to fit to the training test
image datasets. The model was trained using 50 epochs and it achieved an accuracy
of 97.01% and the testing was conducted and the test accuracy was found to be 91%.

The acquisition of the image is done by Pi camera, the ATmega8 camera module v2
replaces the original camera module. It attaches via a 15cm ribbon cable to the USB
port on the ATmega8. This camera works with all modules of ATmega8 1, 2 and 3.
The original image which is captured by ATmega8 which is in jpeg format. Since
jpeg compression technique is a lossy compression, quality of image is reduced and
does not support layered images. In this project it is difficult to differentiate between
the dry and wet Turmeric in the JPEG format, so the image is converted into gray
scale image, which is a range of shades of gray without apparent size.
The darkest possible shade is black which is a total absence of transmitted or
reflected light, the lightest possible shade is white. Gray scale (or a gray level) image
is simply one in which the only sizes are shades of gray. The reason for
differentiating such images from any other sort of size image is that less information
needs to be provided for each pixel. Often, the grayscale intensity is stored as an 8-
bit integer giving 256 possible different shades of gray from black to white. If the
levels are evenly spaced, then the difference between successive gray levels is
significantly better than the gray level resolving power of the human eye. Gray scale
images are very common, in part because much of today’s display and image capture
hardware can only support 8-bit images. To be more in specific with the processing
the image, the gray level image is then further converted into binary image, which is
a digital image that has only two possible values for each pixel. Typically, the two
sizes used for a binary image are black and [Link] images are also called bi-
level or two-level. This means that each pixel is stored as a single bit – i.e., a 0 or 1.
The names black- and white between monochrome or monochromatic are often used
for this concept but may also designate any images that have only one sample per
pixel, such as gray scale images. This kind od images can often arise in digital image
processing as masks or as the result of certain operations such as segmentation,
thresholding and dithering. The above two steps of conversion makes the kNN
algorithm easy to identify the dry and wet Turmeric. The purpose of the k Nearest
Neighbors (kNN) algorithm is to use a database in which the data points are
separated into several separate classes to predict the classification of a new sample
point. The major software requirement in the project of Robotic Arm for Trash
Collecting and Seperating Robot is a PuTTY software which is a free and open-
source terminal. In computing the software application which connects the PuTTY
software to the ATmega8 is a TightVNC server which is a cross-platform free and
opensource remote desktop software application. It uses and extending the RFB
protocol of Virtual Network Computing (VNC) to allow end-users to control another
computer's screen remotely. So once the software and all the hardware parts is
implemented the output of the system is initially picking of garbage and placing it to
the respective segregation models.
The basic function of a pick and place robot is done by its [Link] of freedom
implement the linear and rotational movement of the body and Degrees of movement
imply the number of axis the body can move. In this project using USB cable, which
is a proprietary audio/video interface for transmitting uncompressed video data and
compressed or uncompressed digital audio data from an USB-compliant source
device, such as a display controller, to a compatible computer monitor, video
projector, digital television, or digital audio device. USB is a digital replacement for
analog video standards
 CHAPTER 3
PROJECT DESCRIPTION

3.1 AIM AND OBJECTIVE OF THE PROJECT

The main aim of the project is to design a smart Turmeric Size segregation which
will help in keeping our environment clean and also eco-friendly. We are inspired
from Swachh Bharat Mission. Nowadays, technologies are getting smarter day-to-
day so as to clean the environment, we are designing a smart Turmeric Size
segregation by using ATmega8. This smart Turmeric Size segregation management
system is built on the micro-controller-based system having RFID scanner and robotic
arm.

3.1.1 Methodology

 The block diagram of the proposed work shown in project consists of two
modules Sensing and Classifier Unit and Disposal Unit. The sensing unit and
Classifier unit is implemented with five steps capturing of input image, pre-
processing, Median filtering, contrast enhancement and segmentation. The categories
considered here are cotton, bottles, syringe, papers and others. The classification of
turmeric is based on features extracted from Gray Level Cooccurence Matrix (GLCM)
algorithm. After the segregation process it will be automated to the

 Disposal Unit consisting of ATmega8, relay, buzzer, and motors. The

turmericsegregation model is monitored by a IR sensor, a Water sensor, a gas sensor
and an ultrasonic sensor to identify the status. In addition to the above, there are three
motors to deposit the turmeric based on the classification of turmeric. The medical
turmeric segregation is done automatically in order to avoid diseases that spreading in
hospitals and to reduce the manual process. The algorithm of this proposed system is
given through a sequence of steps
STEP 1: The input image captured by the camera
STEP 2: The sensing and Classifier unit process the image and classifies the turmeric.
STEP 3: The turmeric is detected by the system.
STEP 4: If the system detected the turmeric as plastic, motor 1 will run and it falls to
its respective
bin.
STEP 5: If the system detected the turmeric as cotton, motor 2 will run and it falls to
its respective
bin.
STEP 6: If the system detects the turmeric other than plastic and cotton, motor 3 will
run and it falls
to its respective segregation model.
STEP 7: After the detection process the system will be stopped.

3.2 PROJECT SCOPE

The scope consists of three, the scope of the user, the scope of the location, and the
scope of the system:

 User Scope:
The user's scope consists of people who are in need of help and for working people. It
can be used in Hospitals and office. It is a Image processing wing technology.

 Scope of Location:
The main aim of this project is to reduce human resources and efforts along with the
enhancement of a smart city vision. This project involves people who need help.
Although this project is just a prototype, it is developed almost identical to the actual
situation.
 System scope:
Smart Turmeric Size segregation helps us to reduce the pollution. Many times
garbage Turmeric Size segregation is overflow and many animals like dog or rat
enters inside or near the Turmeric Size segregation. This creates a bad scene. Also,
some birds are also trying to take out garbage from Turmeric Size segregation. This
project can avoid such situations. And can be controlled with Bluetooth and Wi-Fi.
3.3 WORKING

In this project methodology model takes the fundamental process activities of Project

Plan, specification, Analysis, Design, development, validation and evolution and

represents them as separate process phases. Using a waterfall model as a project

development methodology. Smart Turmeric Size segregation has an image

processing interface with autonomous and manual mode of control. The trash is

picked up using robotic arm. The picked-up trash is segregated (metallic dry, metallic

wet, non-metallic dry and non-metallic wet) and dumped into segregation model

attached to the robot which has separate partitions for metallic and non-metallic

trashes. If the collector bin model gets filled it is notified to the person operating the

robot as message in the IMAGE PROCESSING interface. The entire operation of

Turmeric collection can be viewed by the operator through internet using a web

camera attached to the robot.

The robot is operated using an android mobile phone and a laptop. 2 operating modes.

Manual and Autonomous. In manual mode the robot locomotion and trash pickup is

operated using an android phone through Blueterm app. The robot can be controlled

from anywhere in the world by the use of Internet (IMAGE PROCESSING). The trash

is picked up using robotic arm made using servos. The collected trash is transferred to

a collector bin model attached to the robot platform. The collector bin model has

separate partitions for metallic and non-metallic trashes. Another Servo motor

attached to the collector bin model will rotate the segregation model so that the

collected Turmeric will fall into the corresponding partition of the segregation model.

In autonomous mode the robot locomotion and Turmeric pickup is done without

human intervention. In autonomous mode the robot locomotion and Turmeric pickup

is done without human intervention. Other objects are considered as trash and are
picked up by the robotic arm.

Metal detectors placed in the arm check the trash picked to be metallic or non-metallic

and are dumped its corresponding partition in the collector bin model. RFID scanner

placed in the collector bin model monitor the level of the Turmeric in thesegregation

model. If thesegregation model is full it is notified to the operator. A Dust collector is

placed at the bottom of the collector bin model which collects minute dust.

Fig 3.1 BLOCK DIAGRAM

Fig 3.4 . Flow diagram for Turmeric segregation
 CHAPTER 4

SOFTWARE DESCRIPTION
4.1 MATLAB

MATLAB is a high-performance language for technical computing. It integrates

computation, visualization, and programming in an easy-to-use environment where
problems and solutions are expressed in familiar mathematical notation. Typical uses
include:

 Math and computation

 Algorithm development

 Modeling, simulation, and prototyping

 Data analysis, exploration, and visualization

 Scientific and engineering graphics

 Application development, including Graphical User Interblood image building

MATLAB is an interactive system whose basic data element is an array that does not
require dimensioning. This allows you to solve many technical computing problems,
especially those with matrix and vector formulations, in a fraction of the time it would take
to write a program in a scalar noninteractive language such as C or [Link] name
MATLAB stands for matrix laboratory. MATLAB was originally written to provide easy
access to matrix software developed by the LINPACK and EISPACK projects, which
together represent the state-of-the-art in software for matrix [Link] has
evolved over a period of years with input from many users.
In university environments, it is the standard instructional tool for introductory and
advanced courses in mathematics, engineering, and science. In industry, MATLAB is the
tool of choice for high-productivity research, development, and analysis.

MATLAB features a family of application-specific solutions called toolboxes. Very

important to most users of MATLAB, toolboxes allow you to learn and apply specialized
technology. Toolboxes are comprehensive collections of MATLAB functions (M-files) that
extend the MATLAB environment to solve particular classes of problems. Areas in which
toolboxes are available include signal processing, control systems, neural networks, fuzzy
logic, wavelets, simulation, and many [Link] is an interactive programming
environment for scientific computing. MATLAB is heavily used in many technical fields
for data analysis, problem solving, and for experimentation and algorithm development.
Discipline-specific software written in MATLAB, organized into libraries of functions
called toolboxes, is widely used as well. MATLAB has found extensive use as the basis for
computational laboratory work in technical education; more than 1000 textbooks use
MATLAB as a teaching vehicle. MATLAB is a product of The Mathworks of Natick,
Massachusetts, USA. There is general agreement in the technical computing community
that the main reasons for MATLAB's success are its intuitive, concise syntax, the use of
complex matrices as the default numeric data object, the power of the built-in operators,
easily used graphics, and its simple and friendly programming environment, allowing easy
extension of the language. To this one can add the reliability of the numerical methods on
which the operators are based.
4.2 NAMING VARIABLES

Variable names consist of a letter followed by any number of letters, digits or

[Link] is [Link] names can be of any length, however,
MATLAB uses only first N characters, where N is given by the function namelengthmax.
SAVING YOUR WORK

The save command is used for saving all the variables in the workspace, as a file with .mat
extension, in the current directory.
The MATLAB system consists of five main parts:

The MATLAB language.

This is a high-level matrix/array language with control flow statements, functions, data
structures, input/output, and object-oriented programming features. It allows both
"programming in the small" to rapidly create quick and dirty throw-away programs, and
"programming in the large" to create complete large and complex application programs.

The MATLAB working environment.

This is the set of tools and facilities that you work with as the MATLAB user or
programmer. It includes facilities for managing the variables in your workspace and
importing and exporting data. It also includes tools for developing, managing, debugging,
and profiling M-files, MATLAB's applications.

Handle Graphics.
This is the MATLAB graphics system. It includes high-level commands for two-
dimensional and three-dimensional data visualization, image processing, animation, and
presentation graphics. It also includes low-level commands that allow you to fully
customize the appearance of graphics as well as to build complete Graphical User
Interblood images on your MATLAB applications.

The MATLAB mathematical function library.

This is a vast collection of computational algorithms ranging from elementary functions
like sum, sine, cosine, and complex arithmetic, to more sophisticated functions like matrix
inverse, matrix eigenvalues, Bessel functions, and fast Fourier transforms.
The MATLAB Application Program Interblood image (API).
This is a library that allows you to write C and Fortran programs that interact with
MATLAB. It include facilities for calling routines from MATLAB (dynamic linking),
calling MATLAB as a computational engine, and for reading and writing MAT-files.

4.3 MATLAB LANGUAGE

MATLAB has a number of features that distinguish it from standard scientific

programming languages (C and FORTRAN). It is interactive, interpreted rather than
compiled. There are no variable declarations; any value can be assigned to any
variable:First a string, then a 2 by 2 matrix of complex numbers are assigned to the
variable "a". Numbers are, by default, represented as complex, double precision floating
point values. Numeric values are, by default, two-dimensional arrays (matrices). Thus one
may ask for the eigenvalues of an integer constant ( eig(3) ) with no consideration of type
conversion to double or to matrix. Vectors and scalars are not separate types, but rather
arrays with one or both dimensions equal to one. When appropriate, a matrix that has one
(or both) dimensions equal to one is treated as a vector; one may ask for example for the
inner product of a 1 by n and an n by 1 array. The methods that MATLAB offers as built-in
functions include computation of the matrix inverse, the rank, the eigenvalues, the singular
value decomposition, the Moore-Penrose generalized inverse, the LU and QR
factorizations, and other standard operations of linear algebra.

MATLAB notation

MATLAB introduced some notational conveniences that make it easy to express ideas
about matrices more compactly than had been possible. Most notable are the concatenation
operations: [A, B] (the matrix whose columns are the columns of A followed by those of
B) and [A; B] (the vertical concatenation, whose rows are the rows of A followed by those
of B). Other notational innovations include A' for the transpose of the matrix A, A .* B for
the Hadamard (element by element) product of two matrices, and A\b for the computation
of the product of the inverse of a matrix (A) with a vector (b).
MATLAB allows a function to have several outputs, with the syntax [x,y,z] = f(a,b,c). The
m by n matrix all of whose elements are 1 is generated by the function ones(m,n), while
zeros(m,n) and rand(m,n) generate the zero matrix and a matrix with independent uniform
random elements. The identity of order n is known in MATLAB as eye(n).

Avoiding exceptions

Certain common bugs that cause early termination or unpredictable behavior in FORTRAN
and C programs do not do so in MATLAB. Plus and minus infinity are supported values in
MATLAB; they can be the result of a computation and can be written as literal values (Inf,
-Inf). Taking advantage of features in the IEEE-754 standard for floating point, MATLAB
returns appropriate values on divide by zero ( 1 / 0 yields positive infinity, -1 / 0 yields
negative infinity, and 0 / 0 yields Not a Number. ) Writing "past the end" of a matrix does
not cause an error in and of itself, rather the matrix is enlarged (with zeros) to make it big
enough.

Sparse matrices

A MATLAB matrix may be stored internally as a full matrix or as a sparse matrix.

An m by n real, full matrix takes mn 8-byte words to store the elements (twice this if its
imaginary part is nonzero) in addition to a few dozen bytes to store its other attributes, such
as its size. If stored internally as a sparse matrix, then the storage requirement for a real
matrix that has z nonzero elements is z 8-byte words for the nonzero values, and z + n +
1 integer values for indices and pointers that encode the locations of these nonzeros. The
matrix is stored using a compressed sparse columns storage scheme that is common for
sparse matrix software. If only a small fraction of the elements differ from zero, use of the
sparse form can yield a substantial savings in storage. Moreover, MATLAB's operators
take advantage of sparsity and can be far faster when applied to sparse operands. This is
particularly true for the matrix factorization and inversion operators. Some MATLAB
functions produce sparse outputs in all cases:
>> a = speye(3)

a=

(1,1) 1
(2,2) 1
(3,3) 1

>> full(a)

ans =

1 0 0
0 1 0
0 0 1

Note that sparse matrices are displayed as a list of the nonzero elements with their (row,
column) coordinates. The choice of storage format is made by the MATLAB user or
programmer rather than by the MATLAB implementation. The default is full. A matrix can
be coerced to full or to sparse form by use of the functions full and sparse. The nonzeros
can be explicitly listed using ( [row_index, column_index, value] = find(A) ).

Other supported data objects

Signed and unsigned integer data can be created and manipulated. Some operators are,
however, only implemented for doubles. Matrices of short integer types require less storage
than the default 64-bit floating point [Link] (more than two dimensions),
strings, and lists of arbitrary MATLAB objects are also supported:
4.4 HISTORY OF MATLAB

Origins

Cleve Moler is the creator of MATLAB. Moler was a numerical analyst specializing in
matrix computation. In the early 1970s, Moler participated in an effort organized by
Argonne National Laboratory to produce a library of reliable, efficient FORTRAN
subroutines for computing the eigenvalues of matrices (EISPACK) and solving systems of
linear equations (LINPACK). In order to make these packages easier for students to use,
Moler created MATLAB, whose name is a contraction of "Matrix Laboratory." The
original MATLAB was a FORTRAN program, designed for the era of timesharing and
ASCII terminals. It had only one data type (the matrix of complex doubles) and a fixed
collection of 80 functions. Moler used the FORTRAN MATLAB in teaching numerical
analysis at Stanford in 1979. Word of the program reached Jack Little, who grasped the
potential of MATLAB in signal processing and control, and the possibility of making a
successful software product based on MATLAB for the new IBM [Link] and Steve
Bangert developed PC MATLAB by porting Moler's code from FORTRAN to C, adding
user-defined functions (in effect making MATLAB into a programming language rather
than a calculator), improved graphics, and libraries of MATLAB routines, the toolboxes.
Moler, Little, and Bangert formed the Mathworks in 1984, with PC MATLAB as the first
product. Their first sale was an order for ten copies placed by Professor Nick Trefethen at
MIT.
Image processingwth and Development

Jack Little's 100-word, 1983 business plan predicted that the new product would do for the
technical world what Lotus 1-2-3 had done in the business world. MATLAB has indeed
been a commercial success from the beginning, Image processingwing to more than
1,000,000 users and by 2006 to 1,200 Mathworkers, as the employees of Mathworks are
known. MATLAB has, in effect, become the common language for the informal exchange
of software and for algorithmic experiment in technical computing. The company remains
privately held.

There have been several major revisions and enhancements to MATLAB, including an
extended set of graphics tools and primitives, multidimensional arrays and lists (known in
MATLAB as eye arrays), classes and objects, economical storage schemes and algorithms
for sparse matrices, a debugger, a profiler, a GUI builder, a lower cost student edition, and
Just-In-Time (JIT) compilation for improved performance. The computational core has
been upgraded through the incorporation LAPACK (a state-of-the-art library for matrix
computation), as well as software for computation of definite integrals, integration of
ordinary differential equations, and root finders. Toolboxes created by the Mathworks and
other contributors have expanded the scope of MATLAB, adding capabilities in areas such
as , signal and image processing, fuzzy logic, splines, wavelets, statistics, partial
differential equations, bioinformatics, and mathematical finance. SIMULINK, an
extensible block diagram environment for simulation and model-based design appeared as
a second Mathworks product in 1990.

The Mathworks logo is a picture (generated by MATLAB) of a numerical approximation

to the fundamental mode of a vibrating L-shaped membrane, a topic that Moler discussed
in his Stanford Ph.D. thesis in 1965.

4.5 INTERPRETATION, JUST-IN-TIME COMPILATION, AND PERFORMANCE

A simple experiment reveals the performance implications of the MATLAB interpreter and
the improvement possible with JIT compilation. Consider the MATLAB code snippet

>> n = 10^6; a = rand(n,1);

>> tic; a = a + a; toc

Elapsed time is 0.018469 seconds.

This indicates that the library routine used by MATLAB to add two vectors performs this
operation at a rate of about 54 million elements per second (a rate determined by
the memory bandwidth of the machine on which the experiment was run). When the code
is rewritten as a MATLAB loop, the rate is reduced:

>> tic; for i = 1:length(a), a(i) = a(i) + a(i); end, toc

Elapsed time is 0.964865 seconds.

So the interpreter runs this code roughly 50 times slower. When the vector add is placed in
an M-file, however, the JIT compiler is invoked, and the runtime drops to roughly 1.5
times the time taken by the library code.

Naively written MATLAB code can suffer a performance meltdown. Consider

>> clear b; tic; for i = 1:10^5, b(i) = a(i) + a(i); end, toc
Elapsed time is 34.178847 seconds.

Here, the array b is extended by every assignment statement. There being no room in the
previously allocated value to store the new element b(i), the entire array is copied into a
new and larger space. The number of bytes copied Image processingws as the square of the
length of the vectors, a performance disaster. Adding the space allocating statement b =
zeros(size(a)) just before the loop avoids this trap. In MATLAB version 7.4.0 (release
R2007a), current at the time this article was written, the JIT was not powerful enough to
automate this .

In writing a function definition, an input variable can be recycled as an output, providing

preallocated space. Thus, one can write

function a = double(a)

for i = 1:length(a), a(i) = a(i) + a(i); end

and achieve reuse of the storage space of the input variable, avoiding even a single
allocation and an explicit preallocation statement such as result = zeros(size(a)).

4.6 SIMILAR SOFTWARE

There are a number of popular, competitive alternatives to MATLAB that offer a similar
interactive environment for numerical computation, for example: GNU Octave (free),
Scilab (semi-free), and Mathematica (non-free).

MATLAB AND PARALLEL COMPUTERS

With the shift to multi-core processor chips, parallel computers, long in use for demanding
scientific applications, have become the norm in servers, desktops, and laptops.
Programmers have found them quite difficult to use, and there has been widespread
speculation that a parallel version of MATLAB would make parallel machines easier to
use. Many research efforts have aimed at architecting and implementing a parallel
MATLAB-like programming environment (there is an online survey of these). Mathworks
has recently moved to incorporate first a distributed computing model (of loosely coupled
parallel tasks) and now a more complete, parallel version of MATLAB in which multiple
copies of MATLAB, each with its own workspace, can communicate via message passing
and can also cooperatively carry out operation of shared arrays whose elements are
distributed among them.

INTERFACING WITH OTHER LANGUAGES

MATLAB can call functions and subroutines written in the programming

languages C or Fortran.[39] A wrapper function is created allowing MATLAB data types to
be passed and returned. MEX files (MATLAB executables) are the dynamically loadable
object files created by compiling such functions. [40][41] Since 2014 increasing two-way
interfacing with Python was being added.[42][43]Libraries written
in Perl, Java, ActiveX or .NET can be directly called from MATLAB, [44][45] and many
MATLAB libraries (for example XML or SQL support) are implemented as wrappers
around Java or ActiveX libraries. Calling MATLAB from Java is more complicated, but
can be done with a MATLAB toolbox[46] which is sold separately by MathWorks, or using
an undocumented mechanism called JMI (Java-to-MATLAB Interblood image), [47]
[48]
(which should not be confused with the unrelated Java Metadata Interblood image that
is also called JMI). Official MATLAB API for Java was added in 2016. [49]As alternatives
to the MuPAD based Symbolic Math Toolbox available from MathWorks, MATLAB can
be connected to Maple or [Link] also exist to import and export MathML.
[52]

CHAPTER 5

MATERIALS AND METHOD

MODULES
Image Enhancement
Image enhancement techniques have been widely utilized in many applications of
image processing where the subjective quality of images is consequential for
human interpretation. Contrast is a paramount factor in any subjective evaluation
of image quality. Contrast is engendered by the difference in luminance reflected
from two adjacent surfaces. In other words, contrast is the difference in visual
properties that makes an object distinguishable from other objects and the
backImage processingund. In visual perception, contrast is resolute by the
difference in the size and effulgence of the object with other objects. Our visual
system is more sensitive to contrast than absolute luminance; consequently, we can
perceive the world similarly regardless of the considerable transmutations in
illumination conditions. This simply means improvement of the image being
viewed to the (machine or human) interpreter's visual system. Image enhancement
types of operations include contrast adjustment, noise suppression filtering,
application of pseudo size, edge enhancement, and many others.
Image Restoration
The purpose of image restoration is to "compensate for" or "undo" defects which
degrade an image. Degradation comes in many forms such as motion blur, noise,
and camera miscues. In cases like motion blur, it is possible to come up with a
very good estimate of the actual blurring function and "undo" the blur to restore
the original image. In cases where the image is corrupted by noise, the best we
may hope to do is to compensate for the degradation it caused.

Image Analysis
Image analysis is the extraction of meaningful information from images. Image
analysis operations produce numerical or graphical information based on
characteristics of the original image. They break into objects and then classify
them. They depend on the image statistics. Common operations are extraction and
description of scene and image features, automated measurements, and object
classification. Image analyse are mainly used in machine vision applications.
Feature Extraction
Feature extraction involves simplifying the amount of resources required to
describe a large set of data accurately. When performing analysis of complex data
one of the major problems’ stems from the number of variables involved. Analysis
with a large number of variables generally requires a large amount of memory and
computation power or a classification algorithm which over fits the training
sample and generalizes poorly to new samples. Feature extraction is a general term
for methods of constructing combinations of the variables to get around these
problems while still describing the data with sufficient accuracy. All the pre-
processing techniques on image processing are implemented through MATLAB
A CNN machine learning ( /IMAGE PROCESSING) is a Deep Learning algorithm
which can take in an input image, assign importance (learnable weights and biases) to
various aspects/objects in the image and be able to di fferentiate one from the other. The
pre-processing required in a is much lower as compared to other classification
algorithms. While in primitive methods filters are hand-engineered, with enough training,
s have the ability to learn these filters/characteristics.

The architecture of a is analogous to that of the connectivity pattern of Neurons in the

Human Brain and was inspired by the organization of the Visual Cortex. Individual
neurons respond to stimuli only in a restricted region of the visual field known as the
Receptive Field. A collection of such fields overlap to cover the entire visual area.

[Link] ATMEGA8

ATmega8 is an open-source platform used for building electronics projects. ATmega8

consists of both a physical programmable circuit board (often referred to as a
microcontroller) and a piece of software, or IDE (Integrated Development
Environment) that runs on your computer, used to write and upload computer code to
the physical board. The ATmega8 platform has become quite popular with people just
starting out with electronics, and for good reason. Unlike most previous programmable
circuit boards, the ATmega8 does not need a separate piece of hardware (called a
programmer) in order to load new code onto the board – you can simply use a USB
cable. Additionally, the ATmega8 IDE uses a simplified version of C++, making it
easier to learn to program. Finally, ATmega8 provides a standard form factor that
breaks out the functions of the micro- controller into a more accessible package. The
ATmega8 is a microcontroller board based on the ATmega8. It has 14 digital
-input/output pins (of which 6 can be used as PWM outputs), 6 analog inputs, a16 MHz
ceramic resonator, a USB connection, a power jack, an ICSP header, and a reset button.
It contains everything needed to support the microcontroller; simply connect it to a
computer with a USB cable or power it with a AC to DC adapter or battery to get
started. The ATmega8 differs from all preceding boards in that it does not use the FTDI
USB- to-serial driver chip. Instead, it features the Atmega16U2 (Atmega8U2 up to
version R2) programmed as a USB-to-serial converter. Revision 2 of the ATmega8
board has a resistor pulling the 8U2HWB line to ground, making it easier to put into
DFU mode. Revision of the board has the following new features: Pin out: added SDA
and SCL pins that are near to the AREF pin and two other new pins placed near to the
RESET pin, the IOREF that allow the shields to adapt to the voltage provided from the
board. In future, shields will be compatible with both the board that uses the AVR,
which operates with 5V and with the ATmega8 Due that operates with 3.3V. The
second one is a not connected pin that is reserved for future purposes. Stronger RESET
circuit. AT mega 16U2 replace the 8U2. "ATmega8" means one in Italian and is named
to mark the upcoming release of ATmega8 1.0. The ATmega8 and version 1.0 will be
the reference versions of ATmega8,

moving forward. The ATmega8 is the latest in a series of USB ATmega8 boards, and the
reference model for the ATmega8 platform.

Parameters for ATmega8 Description

Microcontroller ATmega 328

Operating voltage 5V
Input voltage(recommended) 7-12 V
Input Voltage (Limits) 6-20 V
Digital I/O pins 14
Analog Input pins 6
DC Current per I/O Pin 40 mA
DC Current for 3.3v Pin 50 mA
Flash Memory 32 KB (ATmega 3280) of which 0.5kb
used by bootloader
SRAM 2 KB (ATmega328)
EEPROM 1 KB (ATmega328)
Clock Speed 16 MHz
Table 4.1 Specification of ATmega8
 [Link] L298N MOTOR DRIVER

The L298N is an integrated monolithic circuit in a 15- lead Multiwatt and PowerSO20
packages. It is a high voltage, high current dual full-bridge driver de-signed to accept
standard TTL logic level sand drive inductive loads such as relays, solenoids, DC and
stepping motors. Two enable inputs are provided to enable or disable the device
independently of the in-put signals. The emitters of the lower transistors of each bridge are
connected together rand the corresponding external terminal can be used for the connection
of an external sensing resistor. An additional Supply input is provided so that the logic
works at a lower voltage.

Features

1) High operating voltage, which can be up to 40 volts;

2) Large output current, the instantaneous peak current can be up to 3A
3) Two built in H-bridge, high voltage, large current, full bridge driver, which can be used
to drive DC motors, stepper motors, relay coils and other inductive loads.
4) Able to drive a two-phase stepper motor or four-phase stepper motor
5) Adopt a high-capacity filter capacitor and a freewheeling diode that protects devices
in the circuit from being damaged by the reverse current of an inductive load,
enhancing reliability.
6) The module can utilize the built-in stabilivolt tube 78M05 to obtain 5v from the
power supply. But to protect the chip of the 78M05 from damage, when the drive
voltage is greater than 12v, an external 5v logic supply should be used.

Fig 4.3 L298N Motor Driver

1. DC motor 1 "+" or stepper motor A+

2. DC motor 1 "-" or stepper motor A-
3. 12V jumper - remove this if using a supply voltage greater than 12V DC. This
enables power to the onboard 5V regulator
4. Connect your motor supply voltage here, maximum of 35V DC. Remove 12V
 jumper if >12V DC
5. GND
6. 5V output if 12V jumper in place, ideal for powering your ATmega8 (etc)
7. DC motor 1 enable jumper. Leave this in place when using a stepper motor.
Connect to PWM output for DC motor speed control.
8. IN1
9. IN2
10. IN3
11. IN4
12. DC motor 2 enable jumper. Leave this in place when using a stepper motor.
Connect to PWM output for DC motor speed control.
13. DC motor 2 "+" or stepper motor B+
14. DC motor 2 "-" or stepper motor B-

[Link] JUMPER WIRES

Fig 4.7 Jumper wires

Jump wires (also called jumper wires) for solderless breadboarding can be obtained
in ready-to-use jump wire sets or can be manually manufactured. The latter can
become tedious work for larger circuits. Ready-to-use jump wires come in different
qualities, some even with tiny plugs attached to the wire ends. Jump wire material
for ready-made or homemade wires should usually be 22 AWG (0.33 mm2) solid
copper, tin-plated wire - assuming no tiny plugs are to be attached to the wire ends.
The wire ends should be stripped 3⁄16 to 5⁄16 in (4.8 to 7.9 mm). Shorter stripped
wires might result in bad contact with the board's spring clips (insulation being
caught in the springs). Longer stripped wires increase the likelihood of short-circuits
on the board. Needle-nose pliers and tweezers are helpful when inserting or
removing wires, particularly on crowded boards.

[Link] USB WEB CAMERA

A USB webcam is a camera that connects to a computer, usually through plugging it

in to a USB port on the machine. The video is fed to the computer where a software
application lets you view the pictures and also transfer them to the Internet. The
software you choose can be set to upload images on a time interval using FTP (file
transfer protocol) to a website, or it can be set to provide a live feed for displaying
on a remote machine or again in a website. When FTP is used the picture on the
website is a static one which is updated regularly at intervals minute by minute, hour
by hour or even longer. This is very easy to set up but the image delay means they
are nowhere near as interesting to watch as a live feed. USB webcam software can
also be used to provide a live feed directly from the computer to your website or
even fed to the Camsecure streaming service to allow large numbers of visitors to
your website to see the feed at the same time. USB webcams can be the small
internal type you usually see for web conferencing and personal use etc. right up to
professional quality out door weather proof webcams. The downside to any USB
type of webcam is the fact that you must have a PC switched on at the location of the
camera to enable the images or video feed to be sent to a website.
 Fig 4.11 USB web camera

[Link] 12V DC MOTOR

Fig 4.12 12V DC motor

Motor1 is a 12V DC geared motor with a .25” motor output shaft and a 2mm rear
encoder shaft. The 2mm shaft works with our ENC300 quadrature encoder to allow
the motor to be used in position control applications. Motor controllers that are rated
for 12V@2A are ideal for controlling this motor. However, motor controllers with
lower current ratings can also be used if they have over-current and overtemperature
protection.

Features
1. 12V – 200RPM –
2. 3.6KG•CM torque DC gearhead motor
3. 30:1 Gear Ratio
4. 2mm rear encoder shaft
5. Good compromise between speed and torque for small robotic designs.
 CHARACTERISTIC VALUE UNIT
Operating voltage 4.5-18 V
Startup torque (kilogram- 3.6 [Link]
force centimeter)
Startup torque (inch- 3.1 [Link]
pound)
Gear ratio 30:1
No-Load current (12V) 0.053 A
Stall Current 1.5 A
No-Load Speed (12V) 200 RPM

Table 4.4 DC motor specification

4.3.3 LCD

We always use devices made up of Liquid Crystal Displays (LCDs) like

computers, digital watches and also DVD and CD players. They have become very
common and have taken a giant leap in the screen industry by clearly replacing the use of
Cathode Ray Tubes (CRT). CRT draws more power than LCD and are also bigger and
heavier. LCD’s have made displays thinner than CRT’s. Even while comparing the LCD
screen to an LED screen, the power consumption is lesser as it works on the basic
principle of blocking light rather than dissipating. All of us have seen an LCD, but no one
knows the exact working of it. Let us take a look at the working of an LCD.A liquid
crystal display or LCD draws its definition from its name itself. It is combination of two
states of matter, the solid and the liquid. LCD uses a liquid crystal to produce a visible
image. Liquid crystal displays are super-thin technology display screen that are generally
used in laptop computer screen, TVs, cell phones and portable video games. LCD’s
technologies allow displays to be much thinner when compared to cathode ray tube (CRT)
technology.
Liquid crystal display is composed of several layers which include two polarized panel
filters and electrodes. LCD technology is used for displaying the image in notebook or
some other electronic devices like mini computers. Light is projected from a lens on a
layer of liquid crystal. This combination of sizeed light with the grayscale image of the
crystal (formed as electric current flows through the crystal) forms the sizeed image. This
image is then displayed on the screen.

A liquid crystal display (LCD) is a thin, flat display device made up of any number
of size or monochrome pixels arrayed in front of a light source or [Link] pixel
consists of a column of liquid crystal molecules suspended between two transparent
electrodes, and two polarizing filters, the axes of polarity of which are perpendicular to
each [Link] the liquid crystals between them, light passing through one would be
blocked by the other. The liquid crystal twists the polarization of light entering one filter to
allow it
An LCD is either made up of an active matrix display grid or a passive display grid. Most
of the Smartphone’s with LCD display technology uses active matrix display, but some of
the older displays still make use of the passive display grid designs. Most of the electronic
devices mainly depend on liquid crystal display technology for their display. The liquid
has a unique advantage of having low power consumption than the LED or cathode ray
tube.
Liquid crystal display screen works on the principle of blocking light rather than emitting
light. LCD’s requires backlight as they do not emits light by them. We always use devices
which are made up of LCD’s displays which are replacing the use of cathode ray tube.
Cathode ray tube draws more power compared to LCD’s and are also heavier and bigger.
Simple facts that should be considered while making an LCD:
The basic structure of LCD should be controlled by changing the applied current.
We must use a polarized light.
Liquid crystal should able be to control both of the operation to transmit or can also able to
change the polarized light.
As mentioned above that we need to take two polarized glass pieces filter in the making of
the liquid crystal. The glass which does not have a polarized film on the surface of it must
be rubbed with a special polymer which will create microscopic grooves on the surface of
the polarized glass filter. The grooves must be in the same direction of the polarized film.
Now we have to add a coating of pneumatic liquid phase crystal on one of the polarized
filter of the polarized glass. The microscopic channel cause the first layer molecule to align
with filter orientation. When the right angle appears at the first layer piece, we should add
a second piece of glass with the polarized film. The first filter will be naturally polarized
as the light strikes it at the starting stage.
Thus the light travels through each layer and guided on the next with the help of molecule.
The molecule tends to change its plane of vibration of the light in order to match their
angle. When the light reaches to the far end of the liquid crystal substance, it vibrates at
the same angle as that of the final layer of the molecule vibrates. The light is allowed to
enter into the device only if the second layer of the polarized glass matches with the final
layer of the molecule. he liquid-crystal display has the distinct advantage of having a low
power consumption than the LED. It is typically of the order of microwatts for the display
in comparison to the some order of milliwatts for LEDs. Low power consumption
requirement has made it compatible with MOS integrated logic circuit. Its other
advantages are its low cost, and good contrast. The main drawbacks of LCDs are
additional requirement of light source, a limited temperature range of operation (between 0
and 60° C), low reliability, short operating life, poor visibility in low ambient lighting,
slow speed and the need for an ac drive.
An LCD is either made up of an active matrix display grid or a passive display
grid. Most of the Smartphone’s with LCD display technology uses active matrix display,
but some of the older displays still make use of the passive display grid designs. Most of
the electronic devices mainly depend on liquid crystal display technology for their display.
The liquid has a unique advantage of having low power consumption than the LED or
cathode ray tube.
Liquid crystal display screen works on the principle of blocking light rather than
emitting light. LCD’s requires backlight as they do not emits light by them. We always use
devices which are made up of LCD’s displays which are replacing the use of cathode ray
tube. Cathode ray tube draws more power compared to LCD’s and are also heavier and
bigger.
Pin Diagram of LCD

Basic structure of an LCD

A liquid crystal cell consists of a thin layer (about 10 u m) of a liquid crystal sandwiched
between two glass sheets with transparent electrodes deposited on their inside faces. With
both glass sheets transparent, the cell is known as transmittive type cell. When one glass is
transparent and the other has a reflective coating, the cell is called reflective type. The
LCD does not produce any illumination of its own. It, in fact, depends entirely on
illumination falling on it from an external source for its visual effect
Making of LCD
Though the making of LCD is rather simple there are certain facts that should be noted
while making it.
The basic structure of an LCD should be controllably changed with respect to the applied
electric current.
The light that is used on the LCD can be polarized.
Liquid crystals should be able to both transmit and change polarized light.
There are transparent substances that can conduct electricity.
To make an LCD, you need to take two polarized glass pieces. The glass which does not
have a polarized film on it must be rubbed with a special polymer which creates
microscopic grooves in the surface. It must also be noted that the grooves are on the same
direction as the polarizing film. Then, all you need to do is to add a coating of nematic
liquid crystals to one of the filters. The grooves will cause the first layer of molecules to
align with the filter’s orientation. At right angle to the first piece, you must then add a
second piece of glass along with the polarizing film. Till the uppermost layer is at a 90-
degree angle to the bottom, each successive layer of TN molecules will keep on twisting.
The first filter will naturally be polarized as the light strikes it at the beginning. Thus the
light passes through each layer and is guided on to the next with the help of molecules.
When this happens, the molecules tend to change the plane of vibration of the light to
match their own angle. When the light reaches the far side of the liquid crystal substance,
it vibrates at the same angle as the final layer of molecules. The light is only allowed an
entrance if the second polarized glass filter is same as the final layer. Take a look at the
figure below.
working of lcd
The main principle behind liquid crystal molecules is that when an electric current is
applied to them, they tend to untwist. This causes a change in the light angle passing
through them. This causes a change in the angle of the top polarizing filter with respect to
it. So little light is allowed to pass through that particular area of LCD. Thus that area
becomes darker comparing to others.
For making an LCD screen, a reflective mirror has to be setup in the back. An electrode
plane made of indium-tin oxide is kept on top and a glass with a polarizing film is also
added on the bottom side. The entire area of the LCD has to be covered by a common
electrode and above it should be the liquid crystal substance. Next comes another piece of
glass with an electrode in the shape of the rectangle on the bottom and, on top, another
polarizing film. It must be noted that both of them are kept at right angles. When there is
no current, the light passes through the front of the LCD it will be reflected by the mirror
and bounced back. As the electrode is connected to a temporary battery the current from it
will cause the liquid crystals between the common-plane electrode and the electrode
shaped like a rectangle to untwist. Thus the light is blocked from passing through. Thus
that particular rectangular area appears blank.
Colour Liquid Crystal Display
Colour LCDs are those that can display pictures in colours. For this to be possible there
must be three sub-pixels with red, green and blue colour filters to create each colour pixel.
For combining these sub-pixels these LCDs should be connected to a large number of
transistors. If any problem occurs to these transistors, it will cause a bad pixel.
One of the main disadvantages of these types of LCDs is the size. Most manufacturers try
to reduce the height than gain it. This is because more transistors and greater pixels will be
needed to increase the length. This will increase the probability of bad pixels. It is very
difficult or also impossible to repair a LCD with bad pixels. This will highly affect the sale
of LCDs.
Working Principle of LCD
The principle behind the LCD’s is that when an electrical current is applied to the liquid
crystal molecule, the molecule tends to untwist. This causes the angle of light which is
passing through the molecule of the polarized glass and also cause a change in the angle of
the top polarizing filter. As a result a little light is allowed to pass the polarized glass
through a particular area of the LCD. Thus that particular area will become dark compared
to other. The LCD works on the principle of blocking light. While constructing the LCD’s,
a reflected mirror is arranged at the back. An electrode plane is made of indium-tin oxide
which is kept on top and a polarized glass with a polarizing film is also added on the
bottom of the device. The complete region of the LCD has to be enclosed by a common
electrode and above it should be the liquid crystal matter.
Next comes to the second piece of glass with an electrode in the form of the rectangle on
the bottom and, on top, another polarizing film. It must be considered that both the pieces
are kept at right angles. When there is no current, the light passes through the front of the
LCD it will be reflected by the mirror and bounced back. As the electrode is connected to a
battery the current from it will cause the liquid crystals between the common-plane
electrode and the electrode shaped like a rectangle to untwist. Thus the light is blocked
from passing through. That particular rectangular area appears blank.

Advantages of an LCD’s:
LCD’s consumes less amount of power compared to CRT and LED
LCD’s are consist of some microwatts for display in comparison to some mill watts for
LED’s
LCDs are of low cost
Provides excellent contrast
LCD’s are thinner and lighter when compared to cathode ray tube and LED

4.3.4 RELAY

The main usage of the Relay was seen in the history for transmitting and receiving the
information, that was called as Morse code where the input signals used to be either 1 or 0,
these change in signals were mechanically noted in terms of ON and OFF of a light bulb or
a beep sound, it means those pulses of 1s and 0s are converted as mechanical ON and OFF
using electromagnets. Later this was improvised and used in various applications. Let’s see
how this electromagnet acts as a switch and why it is named as RELAY. A relay is
classified into many types, a standard and generally used relay is made up of
electromagnets which in general used as a switch. Dictionary says that relay means the act
of passing something from one thing to another, the same meaning can be applied to this
device because the signal received from one side of the device controls the switching
operation on the other side. So relay is a switch which controls (open and close) circuits
electromechanically. The main operation of this device is to make or break contact with
the help of a signal without any human involvement in order to switch it ON or OFF. It is
mainly used to control a high powered circuit using a low power signal. Generally a DC
signal is used to control circuit which is driven by high voltage like controlling AC home
appliances with DC signals from microcontrollers.
A relay is an electrically operated switch. Many relays use an electromagnet to operate a
switching mechanism mechanically, but other operating principles are also used. The first
relays were used in long distance telegraph [Link] voltage is supplied to the
primary circuit, current flows through the coil winding to ground. Whilst doing so, a
magnetic field develops around the primary coil. As the magnetic field builds, it pulls
together the switch contact in the secondary circuit, thus supplying current to the
component being [Link] the relay is switched off the magnetic field is removed
and the sprung plate returns the switch to the open circuit position, thus switching off the
power.
Design of a Relay
An electromechanical relay is basically designed using few mechanical parts like
Electromagnet, a movable armature, contacts, yoke, and a spring/frame/stand, these parts
are showing in the internal pictures of Relay below. All these are arranged logically to
form into a relay.
In electromechanical relays (EMR), contacts are opened or closed using magnets. Solid-
state relays (SSR) have no contacts and switching is totally electronic. Functions
performed by heavy-duty equipment often need switching capabilities of
electromechanical relays. Solid State Relays switch current using non-moving electronic
devices such as silicon controlled rectifiers.
Solid state relays do not have to energize a coil or open contacts. They require lesser
voltage for switching and turn on and off faster because there are no physical parts to
move. Although the absence of contacts and moving parts means that Solid state relays are
not subject to arcing and do not wear out. Contacts on electromechanical relays can be
replaced, whereas entire solid state relays must be replaced when any part becomes
defective. Because of the construction of solid state relays, there is residual electrical
resistance and/or current leakage whether switches are open and closed.
There are many types of relay switches available, but many times transistors and
MOSFETs are used as the main switching device. Transistors provide fast switching
control of the relay coil from various sources. A typical relay switch circuit has the coil
driven by a NPN transistor switch, TR1 as shown depending on the input voltage level.
When the Base voltage of the transistor is zero (or negative), the transistor is cut-off and
acts as an open switch. In this condition, no Collector current flows and the relay coil is
de-energised because being current devices, if no current flows into the Base, then no
current will flow through the relay coil.
Electromagnet:
An Electromagnet plays a major role in the working of a relay. It is a metal which doesn’t
have magnetic property but it can be converted into a magnet with the help of an electrical
signal. We know that when current passes through the conductor it acquires the properties
of a magnet. So, when a metal winded with a copper wire and driven by the sufficient
power supply, that metal can act as a magnet and can attract the metals within its range.
Movable Armature:
Movable armature is a simple metal piece which is balanced on a pivot or a stand. It helps
in making or breaking the connection with the contacts connected to it.
Contacts:
These are the conductors that exist within the device and are connected to the terminals.
Yoke:
It is a small metal piece fixed on a core in order to attract and hold the armature when the
coil is energized.
Spring (optional):
Few relays don’t need any spring but if it is used, it is connected to one end of the
armature to ensure its easy and free movement. Instead of a spring, a metal stand like
structure can be used.
Construction of Relay and its operation:
The following figure shows how a Relay looks internally and how it can be constructed,
On a casing, a core with copper windings (forms a coil) winded on it is placed. A movable
armature consists of a spring support or stand like structure connected to one end, and a
metal contact connected to another side, all these arrangements are placed over the core
such that, when the coil is energized, it attracts the armature. The movable armature is
generally considered as a common terminal which is to be connected to the external
circuitry. The relay also has two pins namely normally closed and normally opened (NC
and NO), the normally closed pin is connected to the armature or the common terminal
whereas the normally opened pin is left free (when the coil is not energized). When the
coil is energized the armature moves and is get connected to the normally opened contact
till there exists flow of current through the coil. When it is de-energized it goes to its initial
position.
The general circuit representation of the relay is as shown in the figure below

How Relay Works:

Relay in NORMALLY CLOSED condition:
When no voltage is applied to the core, it cannot generate any magnetic field and it doesn’t
act as a magnet. Therefore, it cannot attract the movable armature. Thus, the initial
position itself is the armature connected in normally closed position (NC).
Relay in NORMALLY OPENED condition:
When sufficient voltage is applied to the core it starts to create a magnetic field around it
and acts as a magnet. Since the movable armature is placed within its range, it gets
attracted to that magnetic field created by the core, thus the position of the armature is
being altered. It is now connected to the normally opened pin of the relay and external
circuit connected to it function in a different manner.
So finally, we can say that when a coil is energized the armature is attracted and the
switching action can be seen, if the coil is de-energized it loses its magnetic property and
the armature goes back to its initial position.
Different Types of Relay:
Other than the Electromagnetic relay there are many other types of relays which
work on different principles. Its classification is as follows
Types of Relay Based on the principle of operation
Electrothermal relay:
When two different materials are joined together it forms into a bimetallic strip.
When this strip is energized it tends to bend, this property is used in such a way that the
bending nature makes a connection with the contacts.
Electromechanical relay:
With the help of few mechanical parts and based on the property of an
electromagnet a connection is made with the contacts.
Solid State relay:
Instead of using mechanical parts as in electrothermal and electromechanical
relays, it uses semiconductor devices. So, the switching speed of the device can be made
easier and faster. The main advantages of this relay are its more life span and faster
switching operation compared to other relays.
Hybrid relay:
It is the combination of both electromechanical and solid state relays.
Types of Relay Based on the polarity:
Polarized relay:
These are similar to the electromechanical relays but there exists both permanent
magnet and electromagnet in it, the movement of the armature depends on the polarity of
the input signal applied to the coil. Used in telegraphy applications.
Non-polarized relay:
The coil in these relays doesn’t have any polarities and its operation remains
unchanged even if the polarity of the input signal is altered.
Pole and Throw combinations:
Switches can also be classified based on the number of pole and throw combinations.
A pole can be considered as an input terminal and a movable part connected to it, whereas
a throw can be considered as an output terminal. Its classification is as follows
Single pole, single throw (SPST):
It consists of only one pole and one throw. Generally, the path is either closed or
opened (remains untouched to any terminal). A push button is the best example of this
type. When we push the button, the contact is in the closed position and when released the
contact is in the open position, which can be understood from the below image.

Single pole, double throw (SPDT):

This type of switches consists of only one pole but has two throws. So, the contact
is always made to either of the terminals. A slide switch can be considered as its example.
The slider is always connected to either of the contacts i.e., a closed path always exists all
the time if both the terminals are connected to a circuit.

Double pole, single throw (DPST):

It has two poles and a throw. The contacts of it are either opened or closed which is
done simultaneously. Toggle switch works on this property. When the switch is toggled
from one position to another, both the contacts are moved simultaneously.
Double pole, double throw (DPDT):
This type of switches has two poles but the individual pole has two throws. So, it is
named as double throw and the switching action is done similarly and simultaneously for
both the poles. A switch on a standard trimmer is of DPDT because while we are charging
the trimmer and when the switch on the trimmer is in the ON state, it automatically stops
charging means the switches are internally opened in the charging circuit.

Pin Diagram of Relay

Protective relays can prevent equipment damage by detecting electrical
abnormalities, including overcurrent, undercurrent, overloads and reverse currents. In
addition, relays are also widely used to switch starting coils, heating elements, pilot lights
and audible alarms.
Applications of Relay:
 The applications of the relay are limitless, its main function is to
control the high voltage circuit (230V circuit AC) with the low voltage
power supply (a DC voltage).
 Relays are not only used in the large electrical circuits but also used in
the computer circuits in order to perform the arithmetic and
mathematical operations in it.
 Used to control the electric motor switches. To turn ON an electric
motor we need 230V AC supply but in few cases/applications, there
may be a situation to switch ON the motor with a DC supply voltage. In
those cases, a relay can be used.
 Automatic stabilizers are one of its applications where a relay is used.
When the supply voltage is other than the rated voltage, set of relays
sense the voltage variations and controls the load circuit with the help of
circuit breakers.
 Used for the circuit selection if there exists more than one circuit in a
system.
 Used in Televisions. An old picture tube television’s internal circuitry
works with the DC voltage but the picture tube needs a very high AC
 voltage, in order to turn on the picture tube with a DC supply we can
use a relay.
 Used in the traffic signal controllers, temperature controllers.

4.3.1 Power supply

Fig 3.2: Block diagram of power supply

The given block diagram includes following:

• Power supply: a group of circuits that convert the standard ac voltage (120 V,
60 Hz) provided by the wall outlet to constant dc voltage

• Transformer : a device that step up or step down the ac voltage provided by

the wall outlet to a desired amplitude through the action of a magnetic field

• Rectifier: a diode circuits that converts the ac input voltage to a pulsating dc

voltage

• The pulsating dc voltage is only suitable to be used as a battery charger, but not
good enough to be used as a dc power supply in a radio, stereo system, computer
and so on.

• Filter: a circuit used to reduce the fluctuation in the rectified output voltage or
ripple. This provides a steadier dc voltage.

• Regulator: a circuit used to produces a constant dc output voltage by reducing the

ripple to negligible amount. One part of power supply.

Voltage Regulation
• Two basic categories of voltage regulation are:

 line regulation
  load regulation

• The purpose of line regulation is to maintain a nearly constant output voltage when
the input voltage varies.

• The purpose of load regulation is to maintain a nearly constant output voltage when
the load varies

Line Regulation

Load regulation: A change in load current (due to a varying RL) has practically no effect on
the output voltage of a regulator (within certain limits)
• Load regulation can be defined as the percentage change in the output voltage from
no-load (NL) to full-load (FL).

• Where:

VNL = the no-load output voltage

VFL = the full-load output voltage
Types of Regulator
• Fundamental classes of voltage regulators are linear regulators and switching
regulators.

• Two basic types of linear regulator are the series regulator and the shunt regulator .
 • The series regulator is connected in series with the load and the shunt regulator is
connected in parallel with the load.

IC Voltage Regulators
• Regulation circuits in integrated circuit form are widely used.

• Their operation is no different but they are treated as a single device with
associated components.

• These are generally three terminal devices that provide a positive or negative
output.

• Some types have variable voltage outputs.

• A typical 7800 series voltage regulator is used for positive voltages.

• The 7900 series are negative voltage regulators.

• These voltage regulators when used with heatsinks can safely produce current
values of 1A and greater.

• The capacitors act as line filtration.

• Several types of both linear (series and shunt) and switching regulators are
available in integrated circuit (IC) form.

• Single IC regulators contain the circuitry for:

• reference source

• comparator amplifier

• control device

• overload protection

• Generally, the linear regulators are three-terminal devices that provides either
positive or negative output voltages that can be either fixed or adjustable

Fixed Voltage Regulator

• The fixed voltage regulator has an unregulated dc input voltage Vi applied to one
input terminal, a regulated output dc voltage Vo from a second terminal, and the
third terminal connected to ground.

• The series 78XX regulators are the three-terminal devices that provide a fixed
positive output voltage.
 • An unregulated input voltage Vi is filtered by a capacitor C1 and connected to the
IC’s IN terminal.

• The IC’s OUT terminal provides a regulated +12 V, which is filtered by capacitor
C2.

The third IC terminal is connected to ground (GND

• Voltage regulators keep a constant dc output despite input voltage or load changes.

• The two basic categories of voltage regulators are linear and switching.

• The two types of linear voltage regulators are series and shunt.

• The three types of switching are step-up, step-down, and inverting.

• Switching regulators are more efficient than linear making them ideal for low
voltage high current applications.

• IC regulators are available with fixed positive or negative output voltages or

variable negative or positive output voltages.

• Both linear and switching type regulators are available in IC form.

• Current capacity of a voltage regulator can be increased with an external pass

transistor.
 CHAPTER 6

RESULT AND DISCUSSION

The implementation of this invention in fields of Agriculture promotes in the industry.

This simplest technique reduces the work cost and time that can be easily segregate.
This proposed work provides a solution for the industries to segregate the turmeric
size automatically. An sensing and classifier unit based automated classification
system in Agriculture products based on size and shape using Machine Learning
technique are implemented using MATLAB. The disposal unit consists of IR sensor,
camera, controller and motors to dispose various types of size of turmeric products
respectively..
 CHAPTER 7

CONCLUSION AND FUTURE SCOPE

The implementation of this invention in fields of Agriculture promotes in the

industry. This simplest technique reduces the work cost and time that can be easily
segregate. This proposed work provides a solution for the industries to segregate the
turmeric size automatically. An sensing and classifier unit based automated
classification system in Agriculture products based on size and shape using Machine
Learning technique are implemented using MATLAB. The disposal unit consists of
IR sensor, camera, controller and motors to dispose various types of size of turmeric
products respectively..
 REFERENCES
[1] Chaitali Bhangale, Sinh Viralkumar Ganesh, Punetkar Ronak Vijaybhai, Patel
Ronak Shaileshbhai, Dr. R. Anjana, 2020, Smart Garbage Segregation & Handling
System Using Image Processing, International Journal of Creative Research
Thoughts (IJCRT)

[2] Chandradeep Tiwari, Smt. Nagarathna. K, Turmeric Management using Solar

Smartsegregation model, 2017, International Conference on Energy, communication,
data analytics and soft computing (ICECDS).

[3] Chinmay Kolhatkar, Prachi Choudhari, Bhavesh Joshi, Dhruvin Bhuva‖ Smart E-
Turmeric Size segregation,2018, International Conference on Smart city and
emerging technology (ICSCET).

[4] MamtaPandey, AnamikaGowala MrinalJyoti Goswami, ChinmoySaikia And Dr.

Dibyajyoti Bora, 2020, Smart Turmeric Size segregation Using ATmega8,
International Journal of Scientific Research in Engineering and Management
(IJSREM)

[5] Murugaanandam. S, Ganapathy. V and Balaji. R―Efficient IMAGE

PROCESSING Based Smartsegregation model for Clean Environment, 2018,
International Conference on Communication and Signal Processing.

[6] Rishabh Kumar Singhvi, Roshan Lal Lohar, Ashok Kumar, Ranjeet Sharma,
Lakhan Dev Sharma, Ritesh Kumar Saraswat,2019, Image Processing Based Smart
Turmeric Management System: India prospective, Turmeric segregation: Smart
Innovation and Usages 2019 4th International Conference on, pp. 1-6.

[7] R Ramya, G Pooja, D Ranjitha,2019, Smartsegregation models using dry and

wet Turmeric detectors, International Journal of Advanced Research in Computer
Science, 9(Special Issue 3), 164.

[8] Shamin.N, P. Mohamed Fathimal, Raghavendran.R, Kamalesh Prakash, 2019,

Smart Garbage Segregation & Management System Using Turmeric segregation
(Image Processing) & Machine Learning(ML), IEEE 1st International Conference on
Innovations in Information and Communication Technology (ICIICT)

[9] S. Vinoth Kumar, T. Senthil Kumaran, A. Krishna Kumar and Mahantesh

Mathapati, 2017,Smart Garbage Monitoring and Clearance System using Turmeric
segregation, IEEE International Conference on Smart Technologies and Management
for Computing, Communication, Controls, Energy and Materials (ICSTM).
[10] Wesley Pereira, Saurabh Parulekar, Sopan Phaltankar, Vijaya Kamble, 2019,
Smartsegregation model (Turmeric Segregation and Optimisation), IEEE Amity
International Conference on Artificial Intelligence (AICAI)