See discussions, stats, and author profiles for this publication at: [Link]

net/publication/325539340

Integrated Image Processing Functions Using MATLAB GUI

Article in Journal of Computer Science and Technology · March 2013

CITATIONS READS

0 3,381

1 author:

Gullanar M. Hadi
Salahaddin University - Erbil
19 PUBLICATIONS 125 CITATIONS

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Medical Image Segmentation Based on Edge Detection Techniques View project

computer programming languages for computer science depts View project

All content following this page was uploaded by Gullanar M. Hadi on 03 June 2018.

The user has requested enhancement of the downloaded file.

 Journal of Advanced Computer Science and Technology Research, Vol.3 No.1, March 2013, 31-38

Integrated Image Processing Functions Article Info

using MATLAB GUI
Received: 29th April 2012
Nassir H. Salmana, Gullanar M. Hadib, Accepted: 23rd September 2012
Faculty of Computer science, Cihan university,Erbil, Iraq Published online: 1st March 2013
Faculty of Engineering-Software Engineering, Salaheldeen
Univ., Erbil, Iraq
nahu64@[Link], gullanarm@[Link]

ISSN: 2231-8852 © 2013 Design for Scientific Renaissance All rights reserved

ABSTRACT
Graphic User Interface (GUI) was designed to integrate many functions in image processing (IP)
field to callback such that it can perform actions of IP functions such as image segmentation, skin
detection, levelset technique, object extraction, separating color image components and combining
gray images to get color one, adding different noises and preprocessing operations such as different
filtering to remove these noises, and thresholding. All these functions are built and tested using
MATLAB 7.6.0(R2008a) environment. This paper presents a GUI development in Matlab for image
processing.

Keywords: MATLAB GUI, image segmentation, skin detection, levelset , object

extraction, color image, image processing.

1. Introduction

A graphic user interface (GUI) is a pictorial interface to a program. A good GUI can
make programs easier to use by providing them with a consistent appearance and with
intuitive controls like pushbuttons, list boxes , sliders, menus, and so forth. There are three
principle elements required to create a MATLAB graphic user interface: (1)-Components:
like pushbuttons, labels, edit box …,(2)-figures: to arrange the components of a GUI, (3)-
callbacks : integrated IP functions to perform an actions) , for more details see Ch-10 in
(Stephen,2002).
In this paper many functions in image processing field were integrated to callback. For
example; vehicle number plate segmentation and extraction, where according to the image
segmentation, the shape of an object can be described either in terms of its boundary or in
terms of the region it occupies. The objective of segmentation technique in this paper is to
partition a given image into regions or components for extracting objects from an image (i.e
vehicle number plate segmentation and extraction) based on examining an image on a pixel-
by-pixel basis and on utilizing the image information in a prescribed neighborhood to
established boundaries between regions in order to obtain good segmentation results (Pitas,
 Journal of Advanced Computer Science and Technology Research, Vol.3 No.1, March 2013, 31-38

2000). See other functions in the next section. in (Nassir,2008) it built image processing
toolbox using MATLAB menu for some user and built functions. Mathwork group built
many functions in MATLAB that are especially useful for image processing, such as imread,
imfinfo, and imwrite. And others from the online image processing toolbox, User's Guide-
"Getting Started" - "What is Image Processing Toolbox?". The Image Processing Toolbox
provides a set of tools, which allow you to view and manipulate images. A few classic things
that the Image Processing Toolbox allows you to do are: histogram equalization (imhist),
filtering (imfilter), fast Fourier transform (fft2), converting color images to grayscale
(rgb2gray), edge detection (edge), reading, displaying and saving images.
This article was distributed as follows: 1) introduction, 2) GUI callback IP functions, 3) GUI
design steps, 4) results and 5) conclusion.

2. Theoretical Considerations

2.1 GUI callback functions

In this paper a set of MATLAB files were built and then used to implement a set of
functions in image processing field (in addition to image segmentation explained above ) as
seen in figures 1 and 2.

Fig.1. Shows the design of the GUI Fig. 2. Shows the GUI figure after running
the main function.

These functions were modified and tested through GUI. Following a short description for
these functions:
1-Level set method: In mathematics, a level set of a real-valued function f of n variables is a
set of the form:
{ (x1,...,xn) | f(x1,...,xn) = c } (1)

where c is a constant; that is, it is the set where the function takes on a given constant
value. When the number of variables is two, this is a level curve (contour line), if it is three
(in 3-D; Surface (Interface) evolution), this is a level surface, and for higher values of n the

32
 Journal of Advanced Computer Science and Technology Research, Vol.3 No.1, March 2013, 31-38

level set is a level hypersurface. Level set methods are used for the implementation of
curve/interface evolution under various forces. In this method many modified functions were
used (BarisSumengen, 2005 & Matlab [Link],2008).
a) function evolve2D () was used which is a high level function that takes an input, evolves it
N iterations and returns the result. b) Function contour (Z) is a contour plot of matrix Z
treating the values in Z as heights above a plane. A contour plot is the level curves of Z for
some values V. The values V are chosen automatically. The contours are normally colored
based on the current color map. c). Function imcontour; where imcontour(I) was used to
create contour plot of image data and to draw a contour plot of the intensity image I. It was
found that 50 iterations are very good for some images, and the evolution type depend upon
the parameters values in function Phi (BarisSumengen, 2005 & Matlab [Link],2008):see
Fig.3.

Fig.3. The final results of levelset segmentation method to brain image and elapsed time of
processing(28.5 sec)

Fig.4. The vehicle number plate and extraction results

phi= evolve2D(phi,dx,dy,0.5,25,[],[],0,[],0,[],[],1,b); also the processing time depend upon

iteration numbers.

33
 Journal of Advanced Computer Science and Technology Research, Vol.3 No.1, March 2013, 31-38

2- Object extraction method: This is a program for extracting objects from an image. It was
written for vehicle number plate segmentation and extraction for example. The input image is
color input image; median filtering the image was used to remove noise, then finding edges,
smoothing image to reduce the number of connected components. Then calculating all
connected components in the image and displaying them in one figure. Finally storing the
extracted image in an array (JenyRajan,2006).see figures(4 & 9).
3-In skin detection method (JenyRajan,2006): at first, Load an RGB image, convert the image
data to doubles and compute skin likelihood for each pixel; show skin-likelihood image;
threshold the likelihood to detect skin; show the original image, but replace the red band or
blue band with the binary skin image, see Fig5. The detector works as follows:
- gathering a collection of images and mark each pixel as "skin" or "non skin"
- creating an RGB histogram for "skin pixels" and another one for "non-skin pixels"
(they are 32x32x32 in size)
- For a particular bin (i.e. pixel colour), the log likelihood of it being skin is:
log(H(R,G,B) / h(R,G,B))

Fig.5. Skin detection result, see the face and the hand in the image (the processing time is
0.935 sec)

where, H is the skin histogram, and h is the non-skin histogram. For a new image, the log
likelihood of each pixel was computed and then threshold the result to decide skin/non-
skin.(Ciarán, Noel & Alan ,2007) ,where testing the black skins has problems in the
decision.
4-In add and remove noise: this action is to explore noise reduction in images (e.g. salt
&pepper(0.1 default intensity value , Guassian(the default mean value is 0.0 and the default
variance value is 0.005 , Speckels ( the default variance value is 0.1...) using linear and
nonlinear filtering techniques [noise removal filter(e.g. median and adaptive(the default filter
34
 Journal of Advanced Computer Science and Technology Research, Vol.3 No.1, March 2013, 31-38

neighborhood is [3 3] , the output image class is of as the input image class. It is easy to add
averaging filter, (Nassir, 2008), see Fig.6.

Fig.6. shows original brain image (left), the noisy image (mid), and the filtered image (right)

5- In GUIdemo to gray image call, in this function another GUI interface was called (took it
from ([Link], 2009) and modified ) through the GUI2011 to implement image brightness
and convert color image to gray image tasks. See Fig 7.

Fig.7. GUI demo to gray image call and control

Fig.8. Split color image into its components (RGB) then combined them to get color one.

35
 Journal of Advanced Computer Science and Technology Research, Vol.3 No.1, March 2013, 31-38

Fig.9. The vehicle number plate connected components

3. GUI Design steps

3. 1 The Blueprint of a GUI figure

At first, it is necessary to know what is the objective to have in the GUI figure (the final
user interface), such as how many input/output images/plots, how many other kinds of
control objects, and how to arrange it.
Second, it needs to come up the names for each control objects (including the axes to
show images/plots). Usually, the names (tags) of the objects have two parts: the function of
the object (such as “skin detection”), and the type of the object (such as “Push Button”).see
the main figure design in Fig 1.

3.2 Design the GUI figure based on the blueprint

Suppose that Fig. 1 is the GUI Figure we would like to design (i.e., using guide menu then
property inspector menu to indicate the name of the objects we would like to have in the
program). It includes following types of unicontrols: the Edit Box, the Static Text, the Push
Button and the Axes.
To access to the object properties, select the object, right click the mouse, and select
“property inspector”. And to change the names (tags) of the objects, in the properties, we
change the tags of the objects. The strings can be changed (the words that show the user of
the objects, such as “levelset” and “skin detection”) from the properties of the objects.

3.3 Designing the functions to fulfill the goals

If the designed GUI figure was saved as: GUI2011 (or whatever you want). The
MATLAB will automatically save it as [Link]. And the MATLAB will also
automatically generate the file GUI2011.m associate with this GUI figure. (Therefore, it need

36
 Journal of Advanced Computer Science and Technology Research, Vol.3 No.1, March 2013, 31-38

to carefully avoid saving the figure to be some name existed in your directory). Now, if in the
MATLAB command line input “GUI2011” or whatever name you give to this GUI program,
you would see Fig.2. As shown in Fig.2, It is just an empty GUI program. Some codes will
add in the follows. If this m-file is open, you will find there are some predefined functions:
functionvarargout = GUIdemo(varargin)

This function is to set up the whole figure. Here, we do not need to edit it. (Keep it as it
is.): function GUI2011_OpeningFcn(hObject, eventdata, handles, varargin)
This function is to initialize the GUI figure when it is opened at the first time. Here, we
would like to show a default image in the axes1 with the name in the opening function is
[Link] as logo image. We can add the code as follows:
Here, if the GUI program executes, the following code will get:
functionclosePush_Callback(hObject, eventdata, handles)
Usually a push button named “close” will add in each GUI figure. The function of this button
is to close the whole GUI [Link] add one line in this function: close all;
And all the other functions are built separately then integrated in one file called GUI2011.m.
After running that file , the [Link] is display and from this GUI figure all the hidden
functions are called to perform our tasks in image processing (such as skin detection , level
set, segmentation ,…and so on , as shown in the Fig. (2) , left.

4. Conclusion

A graphic user interface (GUI) is a pictorial interface to a program. A good GUI can
make programs easier to use by providing them with a consistent appearance and with
intuitive controls like pushbuttons, list boxes, sliders, menus, and so forth. The designed GUI
is easy to use and program. The results show that many image processing functions can be
integrated in one file to be called and then get actions. There are very clear results, where the
origin image and the processed result appeared in one figure to compare easy. The levelset
technique and extraction an object method give very accurate and clear results. Finally it is
easy using MATLAB programming to get useful image processing toolbox.

References

Stephen J. Chapman,(2002). Matlab programming for engineers, (2nd ed.) (pp.391-

425).brooks/cole Thomson learning .CA 93950 USA.
I. Pitas .(2000). Digital image processing algorithms and applications. (PP-275-82).John
Wiley &Sons , Inc. U.S.A.
BarisSumengen,Citing websites.A Matlab toolbox implementing Level Set methods., vision
research lab at UC Santa [Link] 2005,from
[Link]
The MathWorks, Inc. Citing [Link] R2008a [Link] .Retrieved 2008, from
[Link]

37
 Journal of Advanced Computer Science and Technology Research, Vol.3 No.1, March 2013, 31-38

JenyRajan. Citing websites. Image segmentation & extraction, Retrieved 2006, from
[Link]
extraction/content/seg.m
Ciarán Ó Conaire, Noel E. O'Connor and Alan F. Smeaton,( 2007). Detector adaptation by
maximising agreement between independent data sources. International Workshop on
Object Tracking and Classification beyond the Visible Spectrum, IEEE.
Nassir H. Salman,( 2008b,15-18 Dec. 2008 ). New image processing toolbox using
MATLAB [Link] presented at image processing ,2008. International Arab
conference on information technology, ACIT2008.
Dr. Yingzi (Eliza) [Link] Websites. Matlab GUI tutorial. Retrieved May, 2009 , from
[Link]

SALMAN, N. H, born in 1960. He received his [Link]. and [Link]. degrees

from Al-Mustansyriah University / Collage of Science in 1983 and 1989
respectively. He received his PhD degree in Image Processing and Pattern
Recognition from Shanghai Jiao Tong University-China in 2002. His
research interests include remote sensing, image processing and image
analysis based on image segmentation and edge detection techniques. Also
he is interesting in computer programming languages, Matlab
programming. From 1982-1998, he worked at Space Research Center -Remote Sensing Dept.
in Baghdad –IRAQ, also he was an assistant professor (from 2002) in the Dept. of Computer
Science-Zarqa Private University-Jordan. Now he is head of Computer Science dept .Cihan
University, Erbil-Iraq.

Gullanar M. Hadi, born in 1964. She received her [Link]. and [Link]. degrees
from Collage of Science, Al-Mustansyriah University, Baghdad –IRAQ in
1985 and 1989 respectively. She received his PhD degree in Opto-
Electronics engineering from Shanghai Jiao Tong University-China in
2004. Her research interests include image processing and nano-materials.
From 1985-2006, she worked at Al-Mustansyriah University , collage of
Science, Baghdad –IRAQ, from 2006-2009 she worked as a lecturer in
several Jordanian University, from 2009 to present she was lecturer in Software Engineering
dept. , Salahaddin University, Erbil-Iraq.

38

View publication stats