International Journal of Scientific & Engineering Research, Volume 4, Issue 4, April-2013 1176

ISSN 2229-5518

HISTOGRAM EQUALIZATION TECHNIQUES AND ITS APPLICATION IN EYE

Bhavana Narain1, A.S.Zadgaonkar1, Sanjay Kumar2

Abstract— Histogram equalization (HE) is commonly used for improving contrast in digital images. It has proved to be a simple and effective image contrast enhancement technique. It is a simple and effective image enhancing technique, however, it tends to change the mean brightness of the image to the middle level of the permitted range, and hence is not very suitable for consumer electronic products, where preserving the original brightness is essential to avoid annoying artifacts In this paper we have studied various Histogram equalization and divide the input histogram according to the criteria .In the first part we have discussed Histogram equalization,In the second part we have differentiate various methods of HE. In third part we have filtered an image and applied the program code in the filtered image to get HE. Finally Discussions and conclusions.

Index Terms— Histogram equalization;minimum mean brightness error; Eye Image

1 INTRODUCTION

——————————  ——————————

Histogram equalization (HE) is a popular technique for enhancing image contrast The basic idea is to map the gray levels based on the probability distribution of the image input gray levels. HE flattens and stretches the dynamic range of an image histogram and gives an overall contrast improvement. In fact,
HE has been applied in various areas, such as medical im- age processing The major difference among
the methods in this family is the criteria used to divide the input histogram. For a given image X, the probability den- sity function p (Xk ) is defined as
p (Xk )=nk/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. Note that p (Xk ) is associated with the histogram of the input image which represents the number of pixels that have a specific intensity . In fact, a plot of nk vs. is known histo- gram of X. The high performance of the HE in enhancing the contrast of an image as a consequence of the dynamic range expansion, Besides, HE also flattens a histogram. Base on information theory, entropy of message source will get the maximum value when the message has uni- form distribution property [1].

2 COMPARITIVE STUDY

2

3

S.No.

Methods of HE

Working Criteria

Brightness preserv-

ing Bi-Histogram Equalization (BBHE)

BBHE separates the input image histogram into two parts based on input mean. After separation, each part is equalized independently.

International Journal of Scientific & Engineering Research, Volume 4, Issue 4, April-2013 1177

ISSN 2229-5518

MULTILEVEL COM-

PONENT BASED HISTOGRAM EQUALIZATION (MCBHE)

The MCBHE algorithm

starts just like the BPBHE algorithm by decomposing the input image I into two Sub images using the original mean brightness [9].

MODIFIED HISTO-

GRAM EQUALIZA- TION (MHE)

MHE is an extension of

WTHE. Here each origi- nal probability density value P(rk) is replaced by a

Constrained PDF value

Pc(rk) yielding:

Hk =( L – 1 ) Pc

(rk ) [10].

3 Method to Detect Eyes

My approach is broken down into two stages: find the face, and then find the eyes. To find the face, I designed two methods: one utilizing the high symmetry of a human face and the other using average face matching. In the first method I scan the image for the region that has the best symmetry, and then perform some optimization to get better results. Also I apply a skin filter (2 types the user can choose from) to the face detection window to further shrink down the search space.
In the second method I scan the image for the region that has the best correlation with the given average face tem- plate. To find eyes I also implemented two ways: rule based one and average eye matching. a) The rule-based method simply means the program tries to find two clusters of dark pixels (eyes are dark) with some constraints applied to them. It takes too long and is highly error prone. b) The average eye matching, however, is extremely fast and gives accurate results, but user must supply the ap- proximate ratio of the face size to the image size. This re- quirement renders this method less practical because ide- ally, user shouldn't tell the program anything other than the image itself.

4 HARDWARE SUPPORT AND ALGORITHM

IMAGES

Original

Image

BBHE

RMSH E

Image1

6.788

5.873

6.3016

Image2

7.33

5.783

6.423

5 DISCUSSION

The comparative study of Histogram Equalization based meth- ods shows that the cases which require higher brightness preser- vation

International Journal of Scientific & Engineering Research, Volume 4, Issue 4, April-2013 1178

ISSN 2229-5518

and not handled well by HE, BBHE and DSIHE, have been properly enhanced by RMSHE. MMBEBHE is the extension of BBHE method that provides maximal brightness preservation. DHE ensures consistency in preserving image details and is free from any severe side effects. BPDHE can preserve the mean brightness better than BBHE, DSIHE, MMBEBHE, RMSHE, MBPHE, and DHE. WMSHE achieves the best

(a) Histogram Pattern of Image1

(a)Original Result (b) BBHE (C) RMSHE

(b) Histogram Pattern of Image2

(a) Original Result (b) BBHE (C) RMSHE

quality through qualitative visual inspection and quantita- tive accuracies of Peak Signal-to- Noise Ratio (PSNR) and
Absolute Mean Brightness Error (AMBE) compared to other state-of-the-art methods. Eye part of image has been filtered and Histogram for original Image,Normalized Im- age, Equalized Image has been plotted.

CONCLUSIONS

Histogram equalization is a simple and effective image enhancing technique. However, in some cases, it tends to change significantly the brightness of an image.

ACKNOWLEDGMENT

I am thankful to my guide Dr. A.S. Zadgaonkar and Dr. Sanjay Kumar and co guide for their encouragement and valuable support.

REFERENCES

[1] Y. Wang, Q. Chen, and B. Zhang, “Image enhancement based on equal area dualistic sub-image histogram equalization method,” IEEE Trans. on Consumer Electronics, vol. 45, no. 1, pp. 68-75, Feb. 1999.

[2] K. Wongsritong, K. Kittayaruasiriwat, F. Cheevasuvit, K. Dejhan, and A Som boonkaew, “Contrast enhancement using multipeak histogram equalization with brightness preserving”, The 1998 IEEE Asia-Pasific

Conference on Circuit and Systems, pp. 24-27, November 1998. [10]. M. Abdullah-Al-Wadud, M. H. Kabir, M. A. A. Dewan, and Oksam Chae,

“A dynamic histogram equalization for image contrast enhancement”, IEEE Trans. Consumer Electronics, vol. 53, no. 2, pp. 593 - 600, May

2007.

[3]. Nicholas Sia Pik Kong, and Haidi Ibrahim, “Improving the visual quality of abdominal magnetic resonance images using histogram equalization”,

In Technology and Applications in Biomedicine, 2008. ITAB 2008.

[4]. S.-D. Chen and A. Ramli, “Contrast enhancement using recursive Mean- Separate histogram equalization for scalable brightness preservation,”

IEEE Trans. on Consumer Electronics, vol. 49, no. 4, pp. 1301-1309,

Nov. 2003.

[5]. S.-D. Chen and A. Ramli, “Minimum mean brightness error Bi-Histogram equalization in contrast enhancement,” IEEE Trans. on Consumer

Electronics, vol. 49, no. 4, pp. 1310-1319, Nov. 2003.

[6]. M. Abdullah-Al-Wadud, Md. Hasanul Kabir, M. Ali Akber Dewan, and Oksam Chae, “A dynamic histogram equalization for image contrast enhancement”, IEEE Trans. Consumer Electron., vol. 53, no. 2, pp. 593-

600, May 2007.

[7]. Haidi Ibrahim, and Nicholas Sia Pik Kong, “Brightness preserving dynamic histogram equalization for image contrast enhancement”, IEEE Trans. Consumer Electronics, vol. 53, no. 4, pp. 1752 - 1758, November

2007.

[8]. Pei-Chen Wu, Fan-Chieh Cheng, and Yu-Kumg Chen, “A Weighting Mean-Separated Sub-Histogram Equalization for Contrast Enhancement”, IEEE Trans. Biomedical Engineering and Computer Science, 2010.

[9]. S. Armato, M. Giegr, C. Moran, J. Blackburn, K. Doi, H. Macmahon, “Computerized detection of pulmonary nodules in CT Scans,” RadioGraphics 1999; 19:1303-1311.

[10]. S. Armato, M. Giegr, C. Moran, J. Blackburn, K. Doi, H. Macmahon,

“Computerized detection of pulmonary nodules in CT Scans,”

International Journal of Scientific & Engineering Research, Volume 4, Issue 4, April-2013 1179

ISSN 2229-5518

 Mrs. Bhavna Narain MCA , M.Phil (CS), has been working in the field of computers since last ten plus years, Currently pursuing Ph.D from Dr. CV Raman University, Kota, Bilas- pur, Chhattisgarh, India. Specialization in computer net- works(adhoc,mesh) and Image Processing.

 Dr. A. S. Zadgaonkar, has obtained B. E. degree in Electrical Engineering from Pt.Ravishankar Shukla University He ob- tained M. E. in 1978 from Nagpur University. His research paper for M. E. was awarded “Best paper” by the Institution of Engineers (India) in the year 1976 & 1977 respectively. He was awarded Ph. D. in 1985 by Indira Gandhi Kala & Sang- eet University, Khairagah for his work on “Acoustical and Mechanical Properties of Wood for Contemporary Indian Musical Instrument Making.” He was awarded Ph. D. in

1986 by Pt. Ravishankar Shukla University on “Investiga- tion of Dynamic Properties of Non-Conducting Materials Using Electrical Analogy.” He is currently adding glory to the post of Vice Chancellor of Dr. C. V. Raman University, Bilaspur(Chhattisgarh).

 Dr.Sanjay Kumar has done B.E. (Electrical),M.E.(Computer

Science and Engineering) and Ph.D. in Computer Science and Engineering. At present he is Asso.Prof. and Head in computer Science Department of Pt. Ravishankar Shukla University, Raipur, Chhattisgarh, India. Computer Net- working and Paralal Computing are area of his interest.