Smart Scan
Shrey Pachauri
Chirag Gupta
Geetika Arora
Ishaan Gaba
Abhinav Maheshwari
Mentor : Dr. Smita Aggrawal
Problem Definition, Project Scope,
and Objectives
1 Problem Definition
This project aims to automate the capture and recognition of handwritten marks
from student answer sheets to reduce errors and improve efficiency.
2 Project Scope
• Automates capture and recognition of handwritten marks.
• Reduces errors in grading and data entry.
• Enhances efficiency and saves time.
• Streamlines the examination process.
3 Objectives
• Enhance Efficiency: Speed up and streamline the capture of key details
from answer sheets.
• Improve Accuracy: Minimize errors in data extraction with advanced algorithms.
• Save Time: Automate processes to reduce administrative workload.
• Simplify Access: Ensure easy retrieval and use of captured data.
Detailed Design
Tools/Platforms Used
• React: Front-end interface development.
• Firebase: Backend data storage and management.
• Python & YOLO: Mark recognition model development and training.
• Roboflow: Dataset preprocessing and augmentation for improved accuracy.
Data Design
• Answer Sheets: Images captured from student answer sheets.
• Marks Tables: Structured data representing marks extracted from the sheets.
• Recognition Outputs: Digitized marks stored in Firebase.
• Metadata: Associated information like student ID, exam date, and sheet identifie
Swimlane Diagram
DFD (LEVEL-1)
User Interface Design
Login Functionality Mark Verification Screen Teacher's Dashboard
The user interface provides a The system displays After authentication , the user
simple Login form to securely recognized marks on a is directed to dashboard to see
authenticate the user and dedicated screen, allowing all the students whose marks
redirect the user to the teachers to verify the accuracy are successfully scanned.
dashboard. of the recognition process.
Cost Analysis
Category Cost(in Rs)
ESP32 Camera 2500
Wires and Batteries 500
Structure/Framework/ 3000
Materials
Miscellaneous Costs 1000
Project Outcomes
1 Final Product/Service 2 Working Prototype
• The final automated marks • The working prototype showcases
recognition system offers a user- the system's capability to capture an
friendly and efficient solution for image, process it, and display the
• educators.
It captures and recognizes marks recognized marks.
from answer sheets automatically. • The prototype has undergone
• This system significantly reduces the testing and validation to ensure
time and effort needed for manual accuracy and reliability.
grading.
Individual Contributions
Team Member 1 Team Member 2
\[Name] led the development of the image \[Name] focused on training the YOLO model and
preprocessing pipeline and integration with optimizing its performance.
Roboflow.
Team Member 3 Team Member 4
\[Name] handled the front-end development \[Name] worked on testing and validating the
using React and integrated the Firebase system, ensuring accuracy and reliability.
backend.
Current Progress
1 Completion of the image preprocessing module
The image preprocessing module has been successfully
developed and integrated into the system.
2 Successful training and deployment of the YOLO
model
The YOLO model has been trained and deployed,
demonstrating accurate recognition of handwritten marks.
3 Development of the basic user interface
The basic user interface has been developed, providing a
foundation for further enhancements.
Future Work Plan
1 Remaining Objectives
The project will focus on finalizing the user interface design
and testing, further optimizing the YOLO model for higher
accuracy, implementing additional features such as batch
processing of answer sheets, and conducting user testing
and gathering feedback for further improvements.
2 Future Steps
The project will continue with the following milestones:
complete UI/UX enhancements and finalize the front-end
by \[Date], optimize and test the recognition model across
different datasets by \[Date], and deploy the final version
of the system and conduct training sessions for users by \
[Date].