International Journal of New Technology and Research (IJNTR)

ISSN: 2454-4116, Volume-3, Issue-3, March 2017 Pages 56-62

Color Image Processing in Digital Image

Dr. Mir Mohammad Azad, Md Mahedi Hasan , Mohammed Naseer K
 component of our discussion of image processing. The term
Abstract— The use of color in image processing is motivated by gray level refers to a scalar measure of intensity that ranges
two principal factors. First, color is a powerful descriptor that from black, to grays, and finally to white.
often simplifies object identification and extraction from a
scene. Color image processing is divided into two major areas:
II. COLOR MODELS
full-color and pseudo-color processing. In the first category, the
images in question typically are acquired with a full-color The purpose of a color model (also called color space or color
sensor, such as a color TV camera or color scanner. In the system) is to facilitate the specification of colors in some
second category, the problem is on of assigning a color to a standard, generally accepted way. In essence, a color model
particular monochrome intensity or range of intensities. Until
is a specification of a coordinate system and a subspace
recently, most digital color image processing was done at the
pseudo color level. However, in the past decade, color sensors within that system where each color model is a specification
and hardware for processing color images have become of a coordinate system and a subspace within that system
available at reasonable prices. The result is that full-color image where each color is represented by a single point. In terms of
processing techniques are now used in a broad range of digital image processing, the hardware-oriented models most
applications, including publishing, visualization, and the commonly used in practice are the RBG (red, green, blue)
Internet.
Index Terms—Image processing, Color Image, Digital Image.
model for color monitors and a broad class of color video
cameras; The CMY (clay, magenta, yellow) and CMYK
I. INTRODUCTION (cyan, magenta Yellow, Black) models for color printings and
the his (hue, saturation, intensity) model, which corresponds
Although the process followed by the human brain in
closely with the way humans describe and interpret color.
perceiving and interpreting color is a physic psychological
phenomenon that is not yet fully understood, the physical A. The RGB color Model
nature of color can be expressed on a formal basis supported In the RGB model, each color appears in its primary
by experimental and theoretical results. spectral components of red, green, and blue. This model is
In 1666, Sir Isaac Newton discovered that when a beam of based on a Cartesian coordinate system. The color subspace
sunlight passes through a class prism, the emerging beam of of interest is the cube shone in Figure: 4(a) in which RGB
light is not white but consists instead of a continuous values are at three corners; cyan, magenta, and yellow are at
spectrum of colors ranging from violet at one end to red at the three other corners; black is at the origin; and white is at the
other. The color spectrum may be divided into six broad corner farthest from the origin.
regions: violet, blue, green, yellow, orange, and red. When Images represented in the RGB color model consist of
viewed in full color, no color in the spectrum ends abruptly, three component images, one for each primary color. When
but rather each color blends smoothly into the next. fed into an RGB monitor, these three images combine on the
Basically, the colors that humans and some other animals phosphor screen to produce a composite color image. The
perceive in an object are determined by the nature of the light number of bits used to represent each pixel in RGB space is
reflected from the object. As illustrated in visible light is called the pixel depth. Consider an RGB image in which each
composed of a relatively narrow band of frequencies in the of the red, green, and blue images is an 8-bit image. Under
electromagnetic spectrum. A body that reflects light that is these conditions each RGB color pixel [that is, a triplet of
balanced in all visible wavelengths appears white to the values ( R,G,B )] is said to have a depth of 24 bits ( 3 image
observer, however, a body that favors reflectance in a limited planes times the number of bits per plane ). The term
range of the visible spectrum exhibits some shades of color. full-color image is used often to denote a 24- bit RGB color
For example, green objects reflect light with wavelengths image. The total number of colors in a 24-bit RGB image is
primarily in the 500 to 570 nm range while absorbing most of (2 to the power 8) whole cube = 16,777,216. RGB color cube
the energy at other wavelengths. corresponding to the diagram in Figure 1.
Characterization of light is central to the science of color.
If the light is achromatic (void of color), its only attribute is
its intensity, or amount. Achromatic light is what viewers see
on a black and white television set, and it has been an implicit

Dr Mir Mohammad Azad, Department of Computer Science and

Engineering, Department of Computer Science and Information Technology,
Shanto Mariam University of Creative Technology, Dhaka, Bangladesh
Md Mahedi Hasan, Department of Business Administration, Prime
University, Dhaka, Bangladesh, Fig 1: Schematic of the RGB color cube. Points along the
Mohammed Naseer K, Department of Computer Science and main diagonal have gray values from black at the origin to
Engineering , Maulana Azad National Urdu University, Campus Bangaluru,
India, white at point (1, 1, 1).

56 www.ijntr.org
 Color Image Processing in Digital Image

Fig 2 shows that an image of the cross-sectional plane is C. The HIS Color Model
viewed simply by feeding the three individual component The modal are about to present, called the HSI (hue,
images into a color monitor. In the component images, 0 saturation, intensity) color model, decouples the intensity
represents black and 255 represents white (note that these are component from the color-carrying information (hue and
gray scale images). saturation) in a color image. As a result, the HSI is an ideal
tool for developing image processing algorithms based on
color description that are natural and intuitive to humans,
Red
who after all the developers and users of these algorithms. We
can summarized by saying that RGB is ideal for image color
generation (as in image capture by a color camera or image
display in a monitor screen).but its use for color descriptions
much more limited.
Green
Color Monitor RGB
III. IMAGE PROCESSING AND COLOR TRANSFORMATION

A. Pseudo color image processing

Blue
Pseudo color (also called as false color) image processing
consists of assigning colors to gray values based on a
specified criterion The term pseudo or false color is used to
differentiate the process of assigning colors to monochrome
Fig2: Generating the RGB image of the cross-sectional color
plane (127, G, B). image from the process associate with true color for human
visualization and interpretation of gray-scale events in an
image or sequence of image. One of the principal motivations
for using color is the fact that human can discern thousands of
color shades and intensities, compared to only two dozen or
so shades of gray.

(R=0) (G=0) (B=0) B. Gray level to color transformation

Finally Fig 3: shows the three hidden surface planes of the This transformation is more general and thus is capable of
achieving a wider range of pseudo color enhancement result
cube generated in the same manner.
than the simple slicing technique discussed in the preceding
section. An approach tat is particularly attractive is shown in
It is of interest to note that acquiring a color image is basically
Fig 4 .Basically, the idea underling this approach is to
the process shown in Fig 2, 3 in reverse. A color image can perform three result are than fed separately into the red, green
be acquired by using three filters, sensitive to red, green, and and blue channels of a color content is modulated by nature of
blue, respectively. When we view a color scene with a the transformation function. Note that these are
monochrome camera equipped with one of these filters, the transformation on the gray-level values of image and are not
result is a monochrome image whose intensity is proportional function of position.
to the response of that filter
The method discussed in the previous section is a special
B. The CMY and AMYK color Models case of the technique just described. There, piecewise linear
As indicated cyan, magenta and Yellow are the secondary colors of function of the gray levels is used to generate colors. The
light, alternatively, the primary colors of pigments. For example, method discussed in this section, on the other hand, can be
when surface coated with cyan, pigment is illuminated with white based on smooth, nonlinear function, which as might be
light, no red light is reflected from the surface. That is, cyan expected gives technique considerable flexibility.
subtracts red light from reflected white light, which itself is
composed of equal amount of red, green and blue light.
Red fr(x,y)
Most devices that deposit colored pigments on paper. Such as color
Transformation
printers and copies require CMY data input or perform an RGB to
CMY conversion internally.
This conversion is performed using the simple operation Green
f(x,y) Transformation fg(x,y)
C 1 R
[ M] = [1] ─ [G] (1)
Y 1 B
Blue
Where, again, the assumption is that all color values have been
Transformation fb(x,y)
normalized to the rang with pure cyan does not contain red (this is,
C=1-R in the question). fb(x,y)
Similarly, pure magenta does not reflect green and pure yellow Fig 4: Functional block diagram for pseudo color image
does not reflect blue. Equation (1) also reveals that RGB values can processing fr, fg, and fb are fed into the corresponding red,
be obtained easily from a set of CMY values by subtracting the green and blue inputs of an RGB color monitor.
individual CMY values from 1.

57 www.ijntr.org
 International Journal of New Technology and Research (IJNTR)
ISSN: 2454-4116, Volume-3, Issue-3, March 2017 Pages 56-62
The type of processing just illustrated is quite powerful in Cr R
helping visualized events of interest in complex image,
c = [ Cg ] = [ G ] . (1)
especially when those events our beyond our normal sensing
capabilities. Fig 5 is an excellent illustration of this. These are Cb B
image of the Jupiter moon Io, shown in pseudo color by
The equation indicates that the components of C are simply
combining several of the sensor images from the Galileo
the RGB components of a color image at a point. We take into
spacecraft, some of which are in spectral regions not visible
account the fact that the color components are a function of
to the eye. However, by understanding the physical and
coordinates (x,y) by using the notation
chemical processes likely to affect sensor response, it is
possible to combine the sensed image into a meaningful Cr(x,y) R(x,y)
pseudo color map.
C(x,y)= [Cg(x,y)] = [ G(x,y)] (2)
Cb(x,y) B(x,y)

For an image of size M x N,there are MN such vector,

C(x,y),for x=0,1,2,......M-1; y= 0,1,2,.........N-1.
It is important to keep clearly in mind that Eq.(2) depicts a
vector whose components are spatial variables in x and y. The
fact that the pixels are now color pixels introduces a factor
that, in its easiest formulation, allows us to process a color
image by processing each of its components image
Fig 5: pseudo color rendition Jupiter Moon Io. separately, using standard gray-scale image processing
method.
The results of individual color component processing are
not always equivalent to direct processing in color vector
space, in which case we must formulate new approaches.
D. Color Transformation
Color transformations; deal with processing the
components of a color image within context of a single color
model.
Fig 6: A close-up (Courtesy of NASA) Formulation
One way to combine sensed image data is by how they show As with gray-level transformation techniques of model
either differences in surface chemical composition or change color transformation using the expression
in the way the surface reflects sunlight. For example, in the
pseudo color image in Fig 6, bright red depict material newly g(x,y) = T[f(x,y)] (1)
ejected from an active volcano on Io, and surrounding yellow Where f(x,y) is a color input image, g(x,y) is the transformed
materials are older sulfur deposits. This image conveys these or processed color output image, and T is an operator on f
characteristics much more readily than would be possible by over a spatial neighborhood of f(x,y).
analyzing the component images individually. The pixel values here are triplets or quartets (i.e., groups of
three or four values) from the color space chosen to represent
C. Basics of Full color image processing the images.
In this section be being study of processing techniques
Analogous to the approach we used to introduce the basic
applicable to full color image. Although they are far from
gray-level transformations. We will restrict attention in this
being exhaustive, the techniques developed in the section
section to color transformations of the form.
follow are illustrative of how full-color image are handled for
a variety of image processing tasks. Full-color image si = T( r1,r2,......,rn ), i = 1,2,........,n (2)
processing approaches fall into two major categories.
where, for notational simplicity, ri and si are variables
a) In first category, we process each component image denoting the color components of f( x,y ) and g( x,y ) at any
individually and then from a composite processed color point ( x,y ), n is the number of color components, and
image from the individually processed components. {T1,T2,.......,Tn} is a set of transformation or color mapping
functions that operate on ri to produce si. Note that n
b) In Second category, we work with color pixels directly.
transformations, Ti, combine to implement the single
Because full-color image have at least three components, transformation function, T, in Equation (1). The color space
color pixels really are vectors. For example, in the RGB chosen to describe the pixels of f and g determines the value
system, each color point in the RGB coordinates system (In of n. If the RGB color space is selected, for example, n=3 and
figure RGB color Model). r1,r2, and r3 denote the red, green, and blue components of
the input image, respectively. If the CMYK or his color
Let C represent an arbitrary vector in RGB color space:
spaces are chosen, n=4 or n=3.

58 www.ijntr.org
 Color Image Processing in Digital Image

Fig 7 shows a high-resolution color image of a bowl of

strawberries and cup of coffee that was digitized from a large
format ( 4" x 5" ) color negative. The second row of the
figure contains the components of the initial CMYK scan. In
these images, black represents 0 and white represents 1 in
each CMYK color component. This we see that the
strawberries are composed of large amounts of magenta and
yellow because the images corresponding to these two
CMYK components are the brightest. Black is used sparingly
and is generally confined to the coffee and shadows within
the bowl of strawberries. When the CMYK image is
converted to RGB, as shown in the third raw of the figure, the
strawberries are seen to contain a large amount of red and
very little ( although some ) green and blue. The last row or
Fig. 7 shows the components of Fig. 7―computed using
Equation, (2) through (4). As expected, the intensity
component is a monochrome rendition of the full-color
original. In addition, the strawberries are relatively pure in
color; they possess the highest saturation or least dilution by
white light of any of the hues in the image, finally, we note
some difficulty in interpreting the hue component.
The problem is compounded by the fact that;
 there is a discontinuity in the his model where 0° and
360° meet, and
 hue is undefined for a saturation of 0 (i.e., for white, Fig 7: A full-color image and its various color-space
black, and pure grays). The discontinuity of the components (Original image courtesy Med-data Interactive.)
model is most apparent around the strawberries,
which are depicted in gray level values near both The conversion calculations are more computationally
black (0) and white (1). The result is an unexpected intense than the intensity transformation itself. Regardless of
mixture of highly contrasting gray levels to the color space selected, however, the output is the same.
represent a single color—red. Figure 8 shows the result of applying any of the
Any of the color space components in Fig. 7 can be used in transformations in Equation (4) through (6) to the image of
conjunction with Equation (2). In theory, any transformation
can be performed in any color model. In practice, however,
some operations are better suited to specific models. For a
given transformation, the cost of converting between
representations must be factored into the decision regarding
the color space in which to implement it. Suppose, for
example, that we wish to modify the intensity of the image in Fig. 8 using k = 0.7.
Fig. 7 using.
g( x, y ) = kf( x, y ) (3) Fig 8: Left side original image and right one Result of
decreasing its intensity by 30 %
Where 0 < k < 1. In the color space, this can be done with the
simple transformation.
S3 = kr3 (4) It is important to note that each transformation defined in
Equation (4) through (6) depends only on one component
where s1 = r1 and s2 = r2. Only his intensity component r3
within its color space.
is modified. In the RGB color space, three components must
be transformed: For example, the red output component, s1, Equation (5) is
independent of the green (r2) and blue (r3) inputs; it depends
si = kri i = 1,2,3. (5)
only on the red (r1) input. Transformations of this type are
The CMY space requires a similar set of linear among the simplest and most used color processing tools and
transformations: can be carried out on a per-color-component basis, as
mentioned at the beginning of our discussion. In the
si = kri + ( 1 – K ) i = 1,2,3. (6) remainder of this section we examine several such
Although the his transformation involves the fewest transformations and discuss a case in which the component
number of operations, the computations required to convert transformation functions are dependent on all the color
an RGB or CMY (K) image to the his space more than offsets components of the input image and, therefore, cannot be done
( in this case ) the advantages of the simpler transformation on an individual color component basis.

59 www.ijntr.org
 International Journal of New Technology and Research (IJNTR)
ISSN: 2454-4116, Volume-3, Issue-3, March 2017 Pages 56-62
IV. COLOR COMPLEMENTS AND SLICING n
0.5 if ∑ ( rj – aj )²> R²0 j=1
Si = { , i=1,2,...,n. (8)
ri otherwise

Here, R0 is the radius of the enclosing sphere (or hyper

sphere for n > 3 )and ( a1, a2,......, an) are the components of
its center (i.e., the prototypical color ). Other useful
variations of Equation (7) and (8) include implementing
multiple color prototypes and reducing the intensity of the
colors outside the region of interest—rather than setting them
to a neutral constant.

Figure 9: Complements on the color circle

V. TONE AND COLOR CORRECTIONS
The hues directly opposite one another on the color circle† of Color transformations can be performed on most desktop
Fig. 9 are called complements. Our interest in complement computers. In conjunction with digital cameras, flatbed
stems from the fact that they are analogous to the gray-scale scanners, and inkjet printers, they turn a personal computer
negatives. As in the gray-scale case, color components are into a digital darkroom—allowing tonal adjustments and
useful for enhancing detail that is embedded in dark regions color corrections, the mainstays of high-end color
of a color image—particularly when the regions are dominant reproduction systems, to be performed without the need for
in size. traditionally outfitted wet processing (i.e., dark-room)
Color Slicing facilities. Although tone and color corrections are useful in
other areas of imaging, the focus of the current discussion is
Highlighting a specific range of colors in an image is useful on the most common uses-photo enhancement and color
for separating objects from their surroundings. reproduction.
Color slicing is either to The effectiveness of the transformations examined in this
 display the colors of interest so that they section is judged ultimately in print. Since these
stand out from the background or , transformations are developed, refined, and evaluated on
 Use the region defined by the colors as monitors, it is necessary to maintain a high degree of color
a mask for further processing. consistency between the monitors used and the eventual
The most straightforward approach is to extend the output devices. In fact, the colors of the monitor should
gray-level slicing techniques. Because a color pixel is an represent accurately any digitally scanned source images, as
n-dimensional quantity, however, the resulting color well as the final printed output. This is best accomplished
transformation functions are more complicated than their with a device-independent color model that related the color
gray-scale counterparts. In fact, the required transformations gamut’s of the monitors and output devices, as well as any
are more complex than the color component transforms other devices being used, to one another. The success of this
considered thus far. This is because all practical color slicing approach is a function of the quality of the color profiles used
approaches require each pixel's transformed color to map each device to the model and the model itself. The
components to be a function of all n original pixel's color model of choice for many color management system (CMS)
components. is the CIE L*a*b model, also called CIELAB (CIE [1977] ).
THE L*a*b color components are given by the following
One of the simplest ways to ―slice‖ a color image is to map equations:
the colors outside some range of interest to a non prominent
neutral color. Neutral color. If the colors of interest are
enclosed by a cube (or hypercube for n > 3) of width W
and centered at a prototypical (e.g., average) color with
components (a1, a2,..........,an), the necessary set of L* = 116.h( Y/YW ) - 16 (9)
transformations is a* = 500[ h ( X/Xw ) – h ( Y/YW ) ] (10)
0.5 if [ | rj – aj | > W/2 ] any 1≤ k ≤ n b* = 200[ h ( Y/Yw ) – h ( Z/ZW ) ] (11)
Si = { , i = 1, 2,............., n. (7)
ri otherwise where
³√ q q > 0.008856
These transformations highlight the colors around the h(q) = {
prototype by forcing all other colors to the midpoint of the 70787q + 16/116 q > 0.008856 (12)
reference color space (an arbitrarily chosen neutral point).
For the RGB color space, for example, a suitable neutral point and Xw , Yw, and Zw are reference white tri stimulus
is middle gray or color (0.5, 0.5, and 0.5). values—typically the white of a perfectly reflecting diffuser
If a sphere is used to specify the color of interest, Equation under CIE standard D65 illumination ( defined by x = 0.3127
(7 ) becomes and y = 0.3290 in the CIE chromaticity diagram of Fig 10.

60 www.ijntr.org
 Color Image Processing in Digital Image

Fig. 10: chromaticity diagram

The L*a*b color space is colorimetric (i.e., colors Fig 11: Tonal correcting for Flat, light (high key), Dark (high
perceived as matching are encoded identically), perceptually key) color image.
uniform ( i.e., color differences among various hues are Fig 11 shows typical transformations used for correcting
perceived uniformly-- see the class paper by Mac Adams three common tonal imbalances—flat, light, and dark images.
[1942] ), and device independent. While not a directly The S-shaped curve in the first row of the figure is ideal for
displayable format (conversion to another color space is boosting contrast. Its midpoint is anchored so that highlight
required), its gamut encompasses the entire visible spectrum and shadow areas can be lightened and darkened,
and can represent accurately the color of any display, print, or respectively. (The inverse of this curve can be used to correct
input device. excessive contrast). The transformations in the second and
third rows of the figure correct light and dark images and are
Like the his system, the L*a*b system is an excellent
reminiscent of the power-law transformations. Although the
decoupled of intensity (represented by lightness L* ) and
color components are discrete, as are the actual
color ( represented by a* for red minus green and b* for green
transformation functions, the transformation functions
minus blue ), making it useful in both image manipulation
themselves are displayed and manipulated as continuous
(tone and contrast editing) and image compression
quantities—typically constructed from piecewise linear or
applications. The principal benefit of calibrated imaging
higher order ( for smoother mappings ) polynomials. Note:
systems is that they allow tonal and color imbalances to be
that the keys of the images in Fig 11 are directly observable;
corrected interactively and independently—that is, in two
they could also be determined using the histograms of the
sequential operations. Before color irregularities, like over-
images color components.
and under-saturated colors, are resolved, problems involving
the image's tonal range are corrected. The tonal range of an
image, also called its key type, refers to its general VI. CONCLUSION
distribution of color intensities. Most of the information in The study in this is an introduction to color image
high-key images is concentrated at high ( or light ) intensities;
processing and covers topics selected to give the reader a
the colors of low-key images are located predominantly at low
solid background in the techniques used in this branch of
intensities; middle-key images lie in between. As in the
image processing. Our treatment of color fundamentals and
monochrome case, it is often desirable to distribute the
intensities o a color image equally between the highlights and color models was prepared as foundation material for a field
the shadows. The following examples demonstrate a variety that is in its own right wide in technical scope and areas of
of color transformations for the correction of tonal and color application. In particular, we focused on color models that
imbalances. we felt are not only useful in digital image processing but
would also provide the tools necessary for further study in
Eg:- Transformations for modifying image tones normally are this area of color image processing. The discussion of pseudo
selected interactively. The idea is to adjust experimentally color and full-color processing on an individual image basis
the image's brightness and contrast to provide maximum
provides a tie to techniques.
detail over a suitable range of intensities. The colors
themselves are not changed. In the RGB and CMY(K)
REFERENCES
spaces, this means mapping all three ( or four ) color
components with the same transformation function; in the his [1] Goutsias, J, Vincent, L., and Bloomberg, D. S. (eds.) [2000].
Mathematical Morphology and Its Applications to Image and
color space, only the intensity component is modified. Signal Processing,Kluwer Academic Publishers, Boston, MA.
[2] . Mallot, A.H. [2000]. Computational Vision, The MIT Press,
Cambridge, MA.

61 www.ijntr.org
 International Journal of New Technology and Research (IJNTR)
ISSN: 2454-4116, Volume-3, Issue-3, March 2017 Pages 56-62
[3] . Marchand-Maillet, S. and Sharaiha, Y. M. [2000]. Binary Digital Computer Science From January 2008 to March 2009 at Dum Dum
Image Processing: a discrete Approach, Academic Press, NY. Motijheel College (Honors Programs), Kolkata,India(Affiliated to the
University of Calcutta (C.U.) and accredited by the National Assessment and
[4] . Mitra, S. K. and Sicuranza, G. L. (eds.) {2000]. Nonlinear Image Accreditation Council (N.A.A.C)) also worked as a Lecturer From 23rd
Processing, Academic Press, NY. December 2009 to August 2012 and As a Senior Lecturer from September
[5] . Edelman, S. [1999]. Representation and Recognition in Vision, 2012 to August 2013 Prime University, Dhaka. Presently Working as an
The MIT Press, Cambridge, MA. Assistant Professor, Prime University, Dhaka, Bangladesh. His areas of
interest include E-commerce, Digital Image, and MIS.
[6] . Lillesand, T. M. and Kiefer, R. W. [1999]. Remote Sensing and
Image Interpretation, John wiley & Sons, NY.
[7] . Mather, P. M. [1999]. Computer Processing of Remotely Sensed
Images: An Introduction, John Wiley & Sons, NY. Mohammed Naseer K was born in
Village Gangondanahalli ,
[8] . Petrou, M. and Bosdogianni, P. [1999]. Image Processing: The
Nayandahalli (Post), Police Station –
Fundamentals, John Wiley & Sons, UK.
Chandra Layout; District - Bangalore,
[9] . Russ, J. C. [1999]. The Image Processing Handbook, 3rd ed., CRC Karnataka, India on 12th
Press, Boca Raton, FL. January,1981.He is pursuing M.Tech in
Computer Science Engineering at
[10] . Smirnov, A. [1999]. Processing of Multidimensional Signals, Jawaharlal Nehru Technological
Springer- Verlag, NY. University (JNTU). He received Master
of Computer Application, 2007 from
[11] . Sonka, M., Hlavac, V., and Boyle, R. [1999]. Image
Bangalore University, also received
Processing, Analysis, and Computer Vision, PWS Publishing,
M.Tech in Information Technology,
NY.
2007 from Karnataka State Open
[12] . Umbaugh, S. E. [1998]. Computer Vision and Image University and Bachelor of Computer Application, 2004 from Bangalore
Processing: A Practical Approach Using CVIPtools, Prentice University, India. He worked as Instructor (CSE) from November 2009 to
Hall, Upper Saddle River, NJ. February 2010 at Maulana Azad National Urdu University. Worked as a
Software Developer for the period of 2 years in CoreBits Technologies and
[13] . Haskell, B.G. Nd Netravali, A.N. [1997]. Digital Pictures: also worked as a Tradesman (MR/AC) for the period of 2 years in ISRO. He
Representation, Compression, and Standards, Perseus worked as an Assistant Professor / Guest faculty member of CSE at
Publishing, NY. Maulana Azad National Urdu University (2010-2014). At present he is
[14] .Jahne, B. [1997]. Digital Image Processing: Concepts, working as a Assistant professor of CSE at Maulana Azad National Urdu
Algorithms, and Scientific Applications, Springer-Verlag, NY. University, India. His areas of interest include Programming, Digital Image
processing, and Computer Network.
[15] .Castleman, K.R. [1996]. Digital Image Processing, 2nd ed.,
Prentice Hall, Upper Sanddle River, NJ

AUTHORS PROFILE
Dr Mir Mohammad Azad was born in
Village – Korer Betka; Post Office –
Mirrer Betka; Police Station - Tangail;
District - Tangail, Bangladesh on 10th
October, 1982.He received PhD in
Computer Science, 2008 from Golden
State University, Master of Computer
Application, 2006 from Bharath Institute
of Higher Education and Research
Deemed University (Bharath University)
and Bachelor of Computer
Application,2004,Bangalore University,
India. He was working as a lecturer and
head of computer science in various colleges in Bangalore and also worked
as an Assistant professor and Vice Principal in different colleges in
Bangalore during the year (2005-2009).He worked as an Assistant
Professor and Head of CSE & CSIT at Shanto Mariam university of
Creative Technology (2010-2014). He is having 18 publications in
international journal in various countries like UK, USA, FRANCE, KOREA,
PAKISTAN and INDIA. At present he is working as an Associate
Professor, Department of Computer Science and Engineering &
Computer Science and Information Technology in Shanto Mariam
university of Creative Technology, Uttara, Dhaka, Bangladesh. His areas
of interest include Computer Architecture, E-commerce, Digital Image
processing, Computer Network, Wireless communication and MIS.

Md. Mahedi Hasan.was born in Vill:

Anantupur, Post:Bonarpara, P.S:
Saghata,Dist: Gaibandha, Bangladesh on
th
13 April 1983.He received Master of
Business Administration (M.B.A.)
Major in MIS, 2009 Degree from Sikkim
Mannipal University Of Health Medical &
Technological Science and Bachelor of
Computer Application (BCA) 2006 Degree
from Bangalore University, India, He was
working as a Lecturer, Department of

62 www.ijntr.org