Enhancement of Medical Images using Histogram Based Hybrid Technique

International Journal of Advanced Engineering, Management and Science (IJAEMS) [Vol-2, Issue-9, Sept- 2016]
Infogain Publication (Infogainpublication.com) ISSN : 2454-1311
www.ijaems.com Page | 1425
Enhancement of Medical Images using Histogram
Based Hybrid Technique
Navjot Kaur1
, Er. Harpal Singh2
¹Research Scholar M-Tech, Computer Science and Engineering, Guru Kashi University, India
²Assiatant Professor, UCCA, Guru Kashi University, India
Abstract — Digital Image Processing is very important area
of research. A number of techniques are available for image
enhancement of gray scale images as well as color images.
They work very efficiently for enhancement of the gray scale
as well as color images. Important techniques namely
Histogram Equalization, BBHE, RSWHE, RSWHE
(recursion=2, gamma=No), AGCWD (Recursion=0,
gamma=0) have been used quite frequently for image
enhancement. But there are some shortcomings of the present
techniques. The major shortcoming is that while enhancement,
the brightness of the image deteriorates quite a lot. So there
was need for some technique for image enhancement so that
while enhancement was done, the brightness of the images
does not go down.
To remove this shortcoming, a new hybrid technique namely
RESWHE+AGCWD (recursion=2, gamma=0 or 1) was
proposed. The results of the proposed technique were
compared with the existing techniques. In the present
methodology, the brightness did not decrease during image
enhancement. So the results and the technique was validated
and accepted. The parameters via PSNR, MSE, AMBE etc. are
taken for performance evaluation and validation of the
proposed technique against the existing techniques which
results in better outperform.
Keywords — Histogram Equalization (HE), BBHE, RSWHE,
AGWCD, PSNR, MSE, Enhancement.
I. INTRODUCTION
Image resolution enhancement is a technique that helps to
obtained high-resolution images from low-resolution images.
It is needed to achieve a good effect of vision, in an improved
effective image resolution, required for a good quality of
images where it is required to adjust in a better size of image.
It is mainly used in practical applications, such as robot
vision, medical system, police system, remote image and
image disposal software [1]. Improved investigation of high
resolution image won the breakthrough progress. Algorithms
[1] that are used for typical image enhancement are:-
• Interpolation nearest neighbour interpolation,
• Bilinear interpolation
• Interpolation cubic spine
The three algorithms are simple and easy to
implement, while the marginal inaccuracy and keystone are
fairly obvious. Process of self-adaptive interpolation uses
edge direction and edge magnitude quantization that are
limited to fit the edge of the image sub-pixel, which prevents
the edge interpolation. It can produce strong, but the different
artifacts that will be apparent due to a single edge and robust
methodology [1].
One of the oldest and most popular image resolution
enhancement methods is Histogram equalization (HE) which
is used to enhance the contrast of the image intensity values
that spreads throughout the range. In contrast control, the
overall brightness of the image is changed. It turns out that the
Gray level transform that we are seeking is simply a scaled
version of the original image's cumulative histogram [2].
The method is useful in images with backgrounds and
foregrounds that are both bright or both dark. In particular, the
method can lead to better views of bone structure in x-ray
images, and to better detail in photographs that are over or
under-exposed. A key advantage of the method is that it is a
fairly straightforward technique and an invertible operator. So
in theory, if the histogram equalization function is known,
then the original histogram can be recovered.
The calculation is not computationally intensive [2].
A disadvantage of the method is that it is indiscriminate. It
may increase the contrast of background noise, while
decreasing the usable signal. Histogram equalization
determines a transformation function designed to produce an
output image with a uniform histogram. Another method is to
generate an image having a histogram corresponding
histogram is specified [2].
II. LITERATURE SURVEY
Chao Zuo (2014) proposed spatially weighted histogram
equalization. Spatially weighted histogram not only considers
the times of each grey value appears in a certain

image, but also takes the local characteristics of each pixel
into account. The experimental results show that the proposed
method Spatially weighted histogram has better performance
than the existing methods, and preserve the original brightness
quite well, so that it is possible to be utilized in consumer
electronic products. To reduce undesired artifacts associated
with the conventional histogram, a weight function according
to each pixel’s spatial activity is introduced to make the
contrast enhancement appropriate to the human observers.
Then the grey scale transform function is calculated by
accumulating this spatially weighted histogram. Finally, the
transform function is modified to make sure that the mean
output intensity will be almost equal to the mean input
intensity. Here the proposed method had achieved visually
more pleasing contrast enhancement while maintaining the
input brightness. More importantly, the amount of calculation
and storage involved in this algorithm is rather low which
makes it more competitive in real-time processing [1].
Ravichandran and Magudeeswaran (2012) proposed mean
brightness preserving Histogram Equalization based
techniques for image enhancement. Generally, these methods
partition the histogram of the original image into sub
histograms and then independently equalize each sub-
histogram with Histogram Equalization. The comparison of
recent histogram based techniques is presented for contrast
enhancement in low illumination environment and the
experiment results are collected using low light environment
images. The histogram modification algorithm is simple and
computationally effective that makes it easy to implement and
use in real time systems [3]. Vinod Kumar (2012), here author
presents about Contrast enhancement of digital images is
conveniently achieved by spreading out intensity values
known as Histogram Equalization. In this paper, author
evaluated the performance of different Histogram
Equalization techniques for gray scale static images. In order
to evaluate, the performance of these techniques, are
examined on the basis of AMBE, PSNR and Entropy metrics.
In this process enhancement techniques are applied on the
images with different sizes and received from different
application fields like real images, medical images etc. It is
well illustrated that Brightness Preserving Dynamic
Histogram Equalization (BPDHE) is the most suitable
technique in terms of mean brightness preservation as it has
least average AMBE value. In terms of PSNR, MPHEBP is
the most suitable technique because it has the highest average
PSNR value. In terms of Entropy, BBHE and RSIHE(r=2) are
the best techniques, since these have the highest average
Entropy values. The performance of BPDHE is not
satisfactory in terms of Entropy. Swati Khidse (2013), here
author proposes as Image enhancement is the first
preprocessing step in image processing, that has the image
with more clarity. In this paper the authors describes various
techniques of image enhancement and compare it with image
fusion techniques, with the help of various error analysis
techniques. Image fusion techniques are assessed using the
various metrics. A comparative study is carried out on
different categories of images [4]. Shi-Chia Huang (2013),
here modified histogram and enhanced contrast in digital
images which improves the brightness of dimmed images via
gamma correction and probability distribution of luminance
pixels. In this, video enhancement with the framing difference
as for producing enhanced and higher quality [14]. Mary Kim
(2008), here new histogram equalization method, called
RSWHE (Recursively Separated and Weighted Histogram
Equalization), for brightness preservation and image contrast
enhancement is worked out which provides image brightness
more accurately and produces images with better contrast
enhancement [10]. Zadbuke (2012) proposed modified
dualistic sub image HE method which preserves the
brightness of the image. Histogram equalization (HE) is one
of the common methods used for improving contrast in digital
images. However, this technique is not very well suited to be
implemented in consumer electronics, such as television
because the method tends to introduce unnecessary visual
deterioration such as the saturation effect. One of the solutions
to overcome this weakness is by preserving the mean
brightness of the input image inside the output image [5].
Sonkar and Parsai (2013) reviewed various image
enhancement schemes for enhancing an image which includes
gray scale manipulation, filtering and Histogram Equalization
(HE). The basic idea of HE method is to re-map the gray
levels of an image. There are different images used in
different time period and comparison on the basis of
subjective and objective parameters. Subjective parameters
are visual quality and computation time and objective
parameters are Peak signal noise ratio (PSNR), Mean squared
error (MSE), Normalized Absolute Error (NAE), Normalized
Correlation, Error Color and Composite Peak Signal to Noise
Ratio (CPSNR) [6].

III. METHDOLOGY
Fig.1.1: Image Enhancement Methodology Flowchart
IV. RESULTS
As the proposed technique is developed using MATLAB, its
results features are explained below: Firstly, a GUI window is
there in which we select the techniques of enhancement such
as HE, BBHE, Contrast or Logarithm, RSWHE, AGCWD,
Proposed Hybrid Technique named as (RESWHE +AGCWD)
with 7 buttons. Exit button is there from existing GUI part,
combining total 8 buttons.
Fig.1.2: Main screens for selecting Enhancement Techniques
After selecting any technique button, input is asked for
Medical Gray Scale image or Medical Color image by
browsing window.
Fig.1.3: Browse window for selecting grayscale or color
image
After selecting any off the Gray Scale or Color images, a
browsing window as shown below in fig 1.4 is used for
selecting or loading an image on which enhancement is to be
done is continued in next steps.
Fig.1.4: Browsing windows for Image Selection
After selecting image, Enhanced Image with Original image
and its histogram are shown below with figures for different
techniques of Enhancement as their procedures follows but
above three steps or figures from 1.2 to 1.4 are same:
(i) HE (Histogram Equalization) implementation for gray
scale images.
Fig.1.5: Output image and original image of HE Technique
on gray scale image.
(ii) HE (Histogram Equalization) implementation for Color
images.
Fig.1.6: Output image and original image of HE Technique
on Color image.

(iii) BBHE (Brightness Preserving Bi-histogram
equalization) implementation for gray scale images.
Fig.1.7: Output image and original image of BBHE
Technique on gray scale image.
(iv) BBHE (Brightness Preserving Bi-histogram
equalization) implementation for Color images.
Fig.1.8: Output image and original image of BBHE
Technique on color image.
v) Contrast enhancement with Mean implementation for
gray scale images.
Fig.1.9: Output image and original image of Contrast
enhancement with Mean Technique on gray scale image.
vi) Logarithm (Contrast stretched and threshold
stretched) Enhancement implementation for gray scale
images.
Fig.1.10: Output image and original image of Logarithm
(Contrast stretched and threshold stretched) Technique on
gray scale image.
vii) RSWHE Enhancement (Recursively Separated and
Weighted Histogram Equalization ) implementation for
gray scale images. Before getting histogram and enhanced
image in this technique recursion value is used to be asked for
input which is used as formula 2r
.
Fig.1.11: Output image and original image of RSWHE
Technique on gray scale image
viii) RSWHE Enhancement (Recursively Separated and
Weighted Histogram Equalization ) implementation for
color images.
Fig.1.12: Output image and original image of RSWHE
Technique on color image
ix) AGCWD Enhancement (Adaptive Gamma Correction
and Weighting Distribution) implementation for gray scale

images. Before getting histogram and enhanced image in this
technique gamma value is used to be asked for input as zero
(NO) or one (YES).
Fig.1.13: Output image and original image of AGCWD
Technique on gray scale image
x) AGCWD Enhancement (Adaptive Gamma Correction
and Weighting Distribution) implementation for Color
images.
Fig.1.14: Output image and original image of AGCWD
Technique on color image
xi) RESWHE+ AGCWD Enhancement (Recursively
Separated and Weighted Histogram Equalization +
Adaptive Gamma Correction and Weighting Distribution)
implementation for gray scale images. Before getting
histogram and enhanced image in this technique gamma value
is used to be asked for input as zero (NO) or one (YES) and
recursion value also asked for input which is used as formula
2r
.
Fig.1.15: Output image and original image of Proposed
(RESWHE+AGCWD) Technique on gray scale image
xi) RESWHE+ AGCWD Enhancement (Recursively
Separated and Weighted Histogram Equalization +
Adaptive Gamma Correction and Weighting Distribution)
implementation for Color images.
Fig.1.16: Output image and original image of Proposed
(RESWHE+AGCWD) Technique on color image
The proposed algorithms has been experimentally worked out
on gray scale and color images. Our performance is
meseaured with various parameters such as PSNR. MSE,
AMBE which are tested on images of gray sclae and color. In
each testing image we have used all image enhancement
techniques such as Histogram equalization (HE), Brightness
preserving bi histogram equalization (BBHE), Contrast with
Mean and Logarithm (Stretched contrast and threshold
stretched), RSWHE, AGCWD and Proposed method
(RESWHE +AGCWD) for comparing our results. These
techniques are compared using parameters PSNR (Peak
Signal-to-Noise Ratio), MSE (Mean Square Error) and AMBE
(Absolute Mean Brightness Error).
V. DISCUSSION
Comparison of these techniques on grayscale images is shown
in Figure 1.17.
Name
Images
Image
1
Image 2 Image 3 Image 4
Original
images
HE
BBHE

Contrast
with Mean
Logarithm
(Contrast
Stretched
and
Threshold
Stretched)
RSWHE
AGCWD
Proposed
Method
(RESWH
E+
AGCWD)
Fig.1.17: Comparison on Grayscale Medical test images
Comparison of these techniques on Color images is shown in
Figure 1.18.
Name of
the Images
Image
1
Image 2 Image 3 Image 4
Original
images
HE
BBHE
Contrast
with Mean
Logarithm
(Contrast
Stretched
and
Threshold
Stretched)
RSWHE
AGCWD
Proposed
Method
(RESWHE
+
AGCWD)
Fig.1.18: Comparison on color Medical test images
The values of Parameters i.e quality metrics for the gray scale
or color images had been inputed by the proposed existing
techniques which is shown in figure 1.17, 1.18 from the table
1.1 and 1.2 below it is verfied that PSNR, MSE, ABME
values are better of our proposed techniques as compared to
the existing techniques.
Table 1.1: PSNR (Peak Signal-to-Noise Ratio), MSE (Mean
Square Error) and AMBE (Absolute Mean Brightness Error)
for gray scale images
Techniq
ues/
Images
Name
1 2 3
PSNR
MSE
AMBE
PSNR
MSE
AMBE
PSNR
MSE
AMBE
HE 58
0.
11
5
81
.4
60
0.0
67
6
1.
3
60
0.
06
1
56
.8
BBHE 64
0.
02
6
33
.0
67
0.0
11
2
0.
9
67
0.
01
3
21
.0

Contrast 58
0.
10
8
46
.4
60
0.0
63
60
0.
06
1
70
.2
Logarith
m
Contrast
56
0.
17
2
60
.7
57
0.1
33
4
4.
6
57
0.
12
9
39
.8
RSWHE 75
0.
00
1
1.
22
75
0.0
01
7.
3
2
75
0.
00
2
9.
58
AGCWD 58
0.
09
7
78
.1
0
62
0.0
43
4
9.
5
64
0.
02
7
38
.1
Reswhe+
AGCWD
73
0.
00
2
4.
66
79
0.0
00
8
3.
3
7
77
0.
00
1
5.
41
Table 1.2: PSNR (Peak Signal-to-Noise Ratio), MSE (Mean
Square Error)and AMBE (Absolute Mean Brightness Error)
for Color images
Techniques/
Images
Name
1 2 3
PSNR
MSE
AMBE
PSNR
MSE
AMBE
PSNR
MSE
AMBE
HE
5
8
0.
11
5
8
1
.
4
60
0.0
65
60
.5
4
60
0.
07
0
59
.7
0
BBHE
6
4
0.
02
6
3
3
.
0
68
0.0
11
20
.3
2
66
0.
01
4
21
.0
5
Contrast
5
8
0.
10
8
4
6
.
4
60
0.0
63
60
0.
06
1
70
.2
5
Logarithm
Contrast
5
6
0.
17
2
6
0
.
7
57
0.1
33
44
.6
9
57
0.
12
9
39
.8
8
RSWHE
7
5
0.
00
1
1
.
2
2
75
0.0
01
7.
73
75
0.
00
1
8.
68
AGCWD
5
8
0.
09
7
7
8
.
1
62
0.0
42
48
.6
1
63
0.
03
2
40
.7
6
0
Reswhe+A
GCWD
7
3
0.
00
2
4
.
6
6
78
0.0
00
9
3.
77
77
0.
00
1
4.
64
The performance of image contrasting or enhancing technique
is compared through the evaluation of quantitative mesure
such as MSE, PSNR and AMBE quality metrics. There is
large improvement in the value of PSNR (Peak Signal to
Noise Ratio) for RSWHE and Our Proposed technique
(RESWHE+AGCWD) from our all existing algorithms. As
MSE (Mean Square error) and AMBE (Absolute Mean
Brightness Error) is less in case of again RSWHE and our
Proposed technique (RESWHE+AGCWD) as shown above in
table 5.1 and 5.2 of gray scale and color images.
The proposed method give better results as compared by
other techniques in term of quality Proposed technique
(RESWHE+AGCWD) shows better result in all parameters
as well in some cases RSWHE also shows next to it results.
Both are about to be nearby quality.
VI. CONCLUSION
A number of techniques are available in the literature for
image enhancement of gray scale images as well as color
images. They work pretty well for images enhancement of the
gray scale as well as color images. Few important techniques
namely Histogram Equalization, BBHE, RESWHE
(recursion=2, gamma=No), AGCWD (Recursion=0,
gamma=0) are used quite frequently for image enhancement.
But there are some short comings of the present techniques.
The major shortcoming is that while enhancement, the
brightness of the image deteriorates quite a lot. So there was
need for some technique for image enhancement so that while
enhancement was done, the brightness of the images does not
go down. To remove this shortcoming, a new hybrid
technique namely RESWHE+AGCWD (recursion=2,
gamma=0 or 1) was proposed. The results of the proposed
technique were compared with the existing techniques. In the
present methodology, the brightness did not decrease during
image enhancement. So the results and the technique was
validated and accepted.
VII. FUTURE SCOPE
Although there was reduced brightness problems while image
enhancement for gray scale and color images, yet the
brightness did reduced to some extent. It can be said that even
if the proposed technique is better as compared to the existing
technique yet there is further scope of improvement in the

designed methodology and further investigation of the
proposed methodology is required for better results.
REFERENCES
[1] Chao Zuo, Qian Chen, Xiubao Sui, and Jianle Ren
(2014), “Brightness Preserving Image Contrast
Enhancement using Spatially Weighted Histogram
Equalization ”, The International Arab Journal of
Information Technology, Vol. 11, No. 1, January 2014
[2] A. V. Kumar, R. R. Choudhary (2012), “A comparative
analysis of image contrast enhancement techniques
based on histogram equalization for gray scale static
images”, International Journal of Computer
Applications, Vol. 45, No. 21, pp. 11-15.
[3] C.G. Ravichandran, V. Magudeeswaran (2012), “An
efficient method for contrast enhancement in still images
using Histogram Modification Framework”, Journal of
Computer Science, Vol. 8, No. 5, pp. 775-779.
[4] Swati Khidse and Meghana Nagori(2013), “A
Comparative Study of Image Enhancement Techniques”,
International Journal of Computer Applications (0975–
8887), Volume 81 – No 15, November 2013.
[5] A. S. Zadbuke (2012), “Brightness preserving image
enhancement using modified dualistic sub image
histogram equalization”, International Journal of
Scientific and Engineering Research, Vol. 3, Issue 2, pp.
1-6.
[6] D. Sonkar, M. P. Parsai (2013), “Comparison of
histogram equalization techniques for image
enhancement of gray scale images of dawn and dusk”,
International Journal of Modern Engineering Research,
Vol. 3, Issue. 4, pp. 2476-2480.
[7] H. D. Cheng, X.J. Shi (2004), “A simple and effective
histogram equalization approach to image
enhancement”, Digital Signal Processing, Vol. 14,
pp.158–170.
[8] H. Kabir, A. A. Wadud, O. Chae (2010), “Brightness
preserving image contrast enhancement using weighted
mixture of global and local transformation functions”,
International Arab Journal of Information Technology,
Vol. 7, No. 4, pp. 403-410.
[9] J. A. Stark (2000),“Adaptive image contrast
enhancement using generalizations of histogram
equalization”, IEEE Transactions on Image Processing,
Vol. 9, No. 5, pp. 889-896.
[10]M. Kim and M. G. Chung (2008), “Recursively
separated and weighted histogram equalization for
brightness preservation and contrast enhancement”,
IEEE Transactions on Consumer Electronics, vol. 54, no.
3, pp. 1389-1397.
[11]R. Maini, H. Aggarwal (2010), “A comprehensive
review of image enhancement techniques”, Journal of
Computing, Volume 2, Issue 3, pp. 8-13.
[12]R. Garg, B. Mittal, S. Garg (2013), “Histogram
equalization techniques for image enhancement”,
International Journal of Electronics and Communication
Technology, pp. 107-111.
[13]R. Kumar, H. Sharma, Suman (2010), “Comparative
study of CLAHE, DSIHE & DHE Schemes”,
International Journal of Research in Management,
Science & Technology, Vol. 1, No. 1, pp. 1-4.
[14]S. C. Huang, F. C. Cheng, Y. S. Chiu (2013), “Efficient
contrast enhancement using adaptive gamma correction
with weighting distribution”, IEEE Transactions on
Image Processing, Vol. 22, No. 3, pp. 1032-1041.
[15]S. D. Chen, A. R. Ramli (2004), “Preserving brightness
in histogram equalization based contrast enhancement
techniques”, Digital Signal Processing, Vol. 14, pp. 413-
428.
[16]S. D. Chen, A. R. Ramli (2003), “Contrast enhancement
using recursive mean-separate histogram equalization for
scalable brightness preservation”, IEEE Transactions on
Consumer Electronics, Vol. 49, No. 4, pp. 1301-1309.
[17]S. S. Bedi, R. Khandelwal (2013), “Various image
enhancement techniques- a critical review”, International
Journal of Advanced Research in Computer and
Communication Engineering, Vol. 2, Issue 3, pp. 1605-
1609.
[18]S. R. Suralkar, A. H. Karode, M. S. Rathi (2012),
“Image Contrast Enhancement Using Histogram
Modification Technique”, International Journal of
Engineering Research & Technology (IJERT), Vol. 1
Issue 7, pp. 1-7.
[19]Y. kim (1997), “Contrast enhancement using brightness
preserving bi-histogram equalization”, IEEE
Transactions on Consumer Electronics, vol. 43, no. 1,
pp. 1-8.

Enhancement of Medical Images using Histogram Based Hybrid Technique

More Related Content

What's hot (18)

Similar to Enhancement of Medical Images using Histogram Based Hybrid Technique (20)

Recently uploaded (20)

Enhancement of Medical Images using Histogram Based Hybrid Technique