Histogram equalization is an uncomplicated and extensively used image distinction enhancement technique. The crucial drawback of histogram equalization is it transforms the brightness of the image. To overcome this drawback, different histogram Equalization methods have been projected. These methods protect the brightness on the result image but, do not have a usual look. Therefore this paper is an attempt to bridge the gap and results after the processed Associate regions are collected into one image. The mock-up result explains that the algorithm can not only improve image information successfully but also remain the imaginative image luminance well enough to make it likely to be used in video arrangement directly.
Study on Contrast Enhancement with the help of Associate Regions Histogram Equalization
1. IJSRD - International Journal for Scientific Research & Development| Vol. 3, Issue 10, 2015 | ISSN (online): 2321-0613
All rights reserved by www.ijsrd.com 402
Study on Contrast Enhancement with the Help of Associate Regions
Histogram Equalization
Shefali Gupta
BPS Mahila Vishwavidyalya khanpur kalan, Sonepat
Abstract— Histogram equalization is an uncomplicated and
extensively used image distinction enhancement technique.
The crucial drawback of histogram equalization is it
transforms the brightness of the image. To overcome this
drawback, different histogram Equalization methods have
been projected. These methods protect the brightness on the
result image but, do not have a usual look. Therefore this
paper is an attempt to bridge the gap and results after the
processed Associate regions are collected into one image. The
mock-up result explains that the algorithm can not only
improve image information successfully but also remain the
imaginative image luminance well enough to make it likely
to be used in video arrangement directly.
Key Word: Histogram equalization, enhancement technique,
AIROH
I. INTRODUCTION
Practically everything around us involves images and image
processing. Analyzing and manipulating images with a
computer is known as image processing. It generally involves
three steps:
1) Import an image with an optical scanner or directly
through digital photography.
2) Manipulate or analyze the image in some way. This
stage can include image enhancement and data
compression, or the image may be analyzed to find
patterns that aren't visible by the human eye. For
example, meteorologists use image processing to
analyze satellite photographs.
3) Output the result. The result might be the image altered
in some way or it might be a report based on analysis of
the image. (Source: kumar et.al)
Histogram equalization can be categorized into two
methods: global and local histogram equalization. Global
histogram equalization uses the histogram information of the
whole input image as its transformation function. This
transformation function stretches the contrast of the high
histogram region and compresses the contrast of the low
histogram region. In general, important objects have a higher
and wider histogram region, so the contrast of these objects
is stretched. On the other hand, the contrast of lower and
narrower histogram regions, such as the background, is lost.
This global histogram equalization method is simple and
powerful, but it cannot adapt to local brightness features of
the input image because it uses only global histogram
information over the whole image. This fact limits the
contrast-stretching ratio in some parts of the image, and
causes significant contrast losses in the background and
other small regions. To overcome this limitation, a local
histogram-equalization method has been developed, which
can also be termed block-overlapped histogram equalization.
Over the years, many variants of HE-based
techniques have been proposed to overcome the problem.
Generally, they can be divided into two main categories:
Automatic – the processing does not require user
intervention
Adjustable – user needs to adjust the parameter to
regulate the degree of enhancement (Source: Soong
chen)
In this paper we propose a Contrast Enhancement
method using Associate Histogram Equalization to preserve
naturalness of images and to improve overall contrast.
Contrast Enhancement Associate Region Histogram
Equalization uses linear interpolation method to make
original image have more uniform histogram distribution.
CESRHE separates the intensity range of the histogram into
k Associate regions and redistributes the pixel intensities
based on Associate Intensity Range of Output Histogram
(AIROH). Results of our method are presented, discussed and
compared with other HE methods in the section IV. The
section V serves as the conclusion of this work.
II. HISTOGRAM EQUALIZATION
Let X={X (i,j)} denote a given image composed of L discrete
gray levels denote as {X0, X1,………XL-1} where X(i,j)
represents an intensity of image at the spatial location (i,j) and
X(i,j) ∈ {X0, X1,………XL-1}.
The histogram provides information for the contrast
and overall intensity distribution of an image [1]. The
histogram of a digital image with gray levels in the range [0,
L-1] is a frequency distribution function defined as overall
intensity distribution of an image. For a given image X, the
probability density function p (Xk) is defined by:
𝑝(𝑥 𝑘) =
𝑛 𝑘
𝑛
For k = 0, 1,. . , L-1, where nk represents the number
of times that the level Xk appears in the input image X and n
is the total number of samples in the input image. The
cumulative density function is defined as:
𝑐(𝑥 𝑘) = ∑ 𝑝(𝑥𝑗)
𝑘
𝑗=0
Where k = 0, 1. . . L - 1. Note that c(X L -1) = 1 by
definition. Histogram equalization is a scheme that maps the
input image into the entire dynamic range, (Xo, XL-1); by
using the cumulative density function as a transform function.
A transform function f(x) is based on the cumulative density
function as:
𝑓(𝑥) = 𝑥0 + (𝑥𝑙−1 − 𝑥0) ∗ 𝑐(𝑥)
Where X L-1 represents the maximum gray level then
the output image of the histogram equalization. Y=y(i,j), can
be expressed as:
𝑦 = 𝑓(𝑥)
= {𝑓(𝑥(𝑖, 𝑗))∀ x(i, j) ∈ X }
One example of the histogram equalization is
illustrated in Fig. 2 and fig. 3, where the first image is an
original image of ‘F16’ and ‘Couple’ and the second one is
the result of the histogram equalization.
2. Study on Contrast Enhancement with the Help of Associate Regions Histogram Equalization
(IJSRD/Vol. 3/Issue 10/2015/080)
All rights reserved by www.ijsrd.com 403
III. CONTRAST ENHANCEMENT USING ASSOCIATE REGIONS
HISTOGRAM EQUALIZATION
Contrast enhancement using associate regions histogram
equalization which is proposed in this paper consists of
following steps:
Leveling the histogram.
Separation of histogram intensity into associate-
intensity range.
Redistribution of Associate intensity range.
Normalization of image brightness.
A. Leveling The Histogram
Histogram of the digital image is normally not smooth and
also some brightness levels are likely to be missed. Therefore,
it is difficult to detect the local maxima of the histogram
without smoothing the histogram. In this step, first, the
disappeared brightness levels are filled up by using the linear
interpolation
The histogram of an image is consisted of many
peaks or modes. Each peak of histogram cannot be easily
detected since the probability of brightness levels fluctuates
and also some brightness levels disappear. The linear
interpolation is employed to fill up the disappeared brightness
levels, while the neighborhoods averaging process is applied
to smooth the histogram. Nine consecutive probabilities of
brightness levels are averaged for the new probability of the
central brightness level. This new probability value of the kth
central brightness level, defined as pn(rk) can be obtained by
the following equation:
pn(rk) = ∫
1
9
∑ p(rk−5+i) for ∶ 5 ≤ k ≤ L − 4
9
i=1
𝑝(𝑟𝑘) 𝑓𝑜𝑟: 𝑘 < 5&𝑘 > 𝐿 − 4
Where pn(rn) = new probability value of the central
gray level
p(rk) = pdf of kth gray level
In order to perform linear interpolation, we apply
1×9 window size on original image. i.e. the edge information
of the original image is added to original image. The pixels
related to the edge are more weighted than original one.
B. Separation of Histogram Intensity into Associate-
Intensity Range.
In this section, the starting and end position of input associate
histogram intensity is described and which depends on split
level‘s’. In this section, the original histogram is decomposed
into k parts (that depends on split level) according to that
intensity level based on its gray level probability density
function. Let that intensity levels are Associate Intensity
Range of Input Histogram (AIRIH).
𝐴𝐼𝑅𝐼𝐻 𝐾 = 𝑅 𝑘
𝑖
− 𝑅 𝑘−1
𝑖
Positions of intensity range of input histogram are given by:
𝑅 𝑘
𝑖
= 𝑋𝑐 𝑚𝑎𝑥
/𝑘
Where Xcmax/k = gray level correspondence to cmax/k
cmax= maximum value of cdf (i.e.=1)
k=1, 2…,.s
S-split level
C. Redistribution of Associate Intensity Range
Associate Intensity Range of Output Histogram (AIROH) is
the output intensity range of associate histogram and it is
proportional to the ratio of no. of pixels of the section to the
total no. of pixels in the original image.
AIROHk =
Nk
Nt
∗ (L − 1)
Where Nk = no of pixels in the kth
section
Nt = total no of pixels in the original image.
Positions of intensity range of output histogram are given by:
𝑅 𝑘
𝑜
= 𝑅0
𝑜
+ ∑ 𝐴𝐼𝑅𝑂𝐻𝑖
𝑘
𝑖=1
Where,𝑅0
𝑜
= 0
and k=1,2,…..s
D. Normalization of Image Brightness
In this step, the mean brightness of the input, µi and the mean
brightness of the output obtained after the equalization
process, µ0 is calculated. In order to shift back the mean
brightness to the mean brightness of the input, we apply the
brightness normalization, as define by equation.
G(x, y) = (
µi
µ0
) y(x, y)
Where G(x.y) is the final output image, y (x,y) is the
output just after the equalization process, x represents
horizontal coordinate and y represents vertical coordinate.
This normalization will make sure that the mean output
intensity is almost equal to the mean input intensity.
IV. RESULTS AND DISCUSSION
In this section we compare the performance of all algorithms
according to three parameters (i) Image Brightness mean, (ii)
Image Contrast – standard Deviation, (iii) Peak Signal to
Noise Ratio (PSNR). These three equations are referred from
the Multi – histogram equalization methods for contrast
enhancement and brightness. The results shown the
brightness preserving capabilities of various methods
considered in this paper. By observing the absolute difference
between the value of brightness in the original images and the
processed images.
V. CONCLUSION
We proposed a contrast enhancement method using associate
region histogram equalization. The significant change in
brightness caused by conventional contrast enhancement
methods may bring undesired artifacts and unnatural look
image. In ARHE we can get more detailed and moderate
histogram by using the weighted average of absolute color
difference. Furthermore, it can preserve naturalness of an
image and prevent significant change in brightness by using
the adaptive scale factor. The experimental results showed
that it prevented excessive enhancement in contrast and
preserved naturalness of an image than conventional
methods. Moreover, since it does not include logarithm and
exponential computation, computation complexity might be
significantly reduced in software/hardware implementation.
Thus, ARHE could be utilized in the consumer electronics,
such as LCD and PDP TV
3. Study on Contrast Enhancement with the Help of Associate Regions Histogram Equalization
(IJSRD/Vol. 3/Issue 10/2015/080)
All rights reserved by www.ijsrd.com 404
REFERENCES
[1] R. C. Gonzalez, “Digital Image Processing,” 2nd
Edition, Prentice Hall, pp. 75 146, 2002.
[2] R. Crane, “A Simplified Approach to Image
Processing,” Prentice Hall, pp. 42-66, 1997.
[3] C. Wang, et al., “Brightness Preserving Histogram
Equalization with Maximum Entropy: A Variational
Perspective,” IEEE Trans. On Consumer
Electronics, Vol. 51, No. 4, pp. 1326-1334, 2005.
[4] Y. T. Kim, et al., "Contrast Enhancement Using
Brightness PreservingBi Histogram Equalization,"
IEEE Trans. Consumer Electronics, Vol. 43, No. 1,
pp. 1-8, 1997.
[5] J. Y. Kim, et al., “An Advanced Contrast
Enhancement Using PartiallyOverlapped Sub-Block
Histogram Equalization,” IEEE Trans. On
Circuitand Systems, Vol. 11, No. 4, pp. 475-484,
2005.
[6] S. D. Chen, and A. R. Ramli, “Contrast
Enhancement using Recursive Mean-Separate
Histogram Equalization for Scalable Brightness
preservation,” IEEE Transactions on Consumer
Electronics, Vol. 49, No. 4, pp.1301-1309, 2003.
[7] M. A. -A. -Wadud, et al., “A Dynamic Histogram
Equalization for Image Contrast Enhancement,”
IEEE Trans. on Consumer Electronics, Vol. 53, No.
2, pp.593-600, 2007.
[8] Z. Y. Chen, et al., “Gray-Level Grouping (GLG) :
An Automatic Method for Optimized Image
Contrast Enhancement – Part I : The Basic Method,”
IEEE Trans. on Image Processing, Vol. 15, No. 8,
pp.2290- 2302, 2006.
[9] G. H. Park, et al., “Image Enhancement Method by
Saturation and Contrast Improvement,” IMID 2007,
Vol. 7, No. 2, pp.1139-1142, 2007.
[10]C.H. Ooi, N.A.M. Isa, Adaptive contrast
enhancement methods with brightness preserving,
IEEE Trans. Consum. Electron. 56 (4) (November
2010) 2543–2551.
[11]Se-Hwan Yun, J.H. Kim, S. Kim, Image
enhancement using a fusion framework of histogram
equalization and Laplacian pyramid, IEEE Trans.
Consum. Electron. 56 (4) (November 2010) 2763–
2771.
[12]N. Sengee, A. Sengee, H.-K. Choi, Image contrast
enhancement using bihistogram equalization with
neighbourhood metrics, IEEE Trans. Consum.
Electron. 56 (4) (November 2010) 2727–2734.
[13]Soong-Der Chen, Abd. Rahman Ramli, Contrast
enhancement using recursive mean-separate
histogram equalization for scalable brightness
preservation, IEEE Trans. Consum. Electron. 49 (4)
(November 2003) 1301–1309.
[14]M. Abdullah-Al-Wadud, et al., A dynamic
histogram equalization for image contrast
enhancement, IEEE Trans. Consum. Electron. 53 (2)
(May 2007) 593–600.
[15]Qing Wang, Rabab K. Ward, Fast image/video
contrast enhancement based on weighted
thresholded histogram equalization, IEEE Trans.
Consum. Electron. 53 (2) (May 2007) 757–764.
[16]Soong-Der Chen, Azizah bt. Suleiman, Scalable
global histogram equalization with selective
enhancement for photo processing, in: Proceedings
of the 4th
International Conference on Information
Technology and Multimedia, Malaysia, November
2008.
[17]H. Ibrahim, N.S.P. Kong, Image sharpening using
sub-regions histogram equalization, IEEE Trans.
Consum. Electron. 55 (2) (May 2009) 891–895.
[18]T. Arici, S. Dikbas, Y. Altunbasak, A histogram
modification framework and its application for
image contrast enhancement, IEEE Trans. Image
Process. 18 (9) (September 2009) 1921 1935.
[19]D. Sheet, H. Garud, A. Suveer, M. Mahadevappa, J.
Chatterjee, Brightness preserving dynamic fuzzy
histogram equalization, IEEE Trans. Consum.
Electron. 56 (4) (November 2010) 2475–2480.
[20]C.H. Ooi, N.A.M. Isa, Quadrants dynamic
histogram equalization for contrast enhancement,
IEEE Trans. Consum. Electron. 56 (4) (November
2010) 2552– 2559.
[21]Der Soong Chen, Manjit Singh Sidhu, Re-evaluation
of automatic global histogram equalization-based
contrast enhancement methods, eJCSIT Electron. J.
Comput. Sci. Inform. Technol. 1 (1) (May 2009) 13–
17.
[22]Rich Franzen, Kodak lossless true color image suite,
http://r0k.us/graphics/ kodak/.
[23]H.R. Sheikh, Z. Wang, L. Cormack, A.C. Bovik,
LIVE image quality assessment database release 2,
http://live.ece.utexas.edu/research/quality.
[24]VQEG, VQEG final report of FR-TV phase II
validation test, 2003.
[25]H.R. Sheikh, M.F. Sabir, A.C. Bovik, A statistical
evaluation of recent full reference image quality
assessment algorithms, IEEE Trans. Image Process.
15 (11) (November 2006) 3440 3451.
Fig. 1: Original Image
Fig. 2: Histogram Equalization