International Journal of Advances in Electrical and Electronics Engineering 69 ISSN: 2319-1112 Image Enhancement Techniques Based on Histogram Equalization Rahul Jaiswal 1, A.G. Rao 2, H.P. Shukla 3 1 M.Tech (ED&T) Student, National Institute of Electronics & Information Technology, Gorakhpur (UP India) (Email id-jaiswal5101.rahul@gmail.com 2 Scientist B National Institute of Electronics & Information Technology, Gorakhpur (UP India) (Email id anurag_govind@yahoo.co.in. 3 Director National Institute of Electronics & Information Technology, Gorakhpur (UP India) (Email id hpshukla123@rediffmail.com, ) Abstract- Histogram equalization is a technique of improving the global contrast of an image by adjusting the intensity Distribution on a histogram. It allows area of lower local contrast to gain a higher contrast without affecting the global contrast. Histogram equalization accomplishes this by effectively spreading out the most frequent intensity values. Histogram Equalization is used to expand the pixel value distribution that increases the perceptional information. The Histogram of an image records the frequency distribution of grey level in that image. The Histogram of an 8 bit image can be thought of as table with 256 entries, or bins indexed from 0 to 255. In bin0 we records the number of times a gray level of 0 occurs; in bin 1 we record the number of times a grey level of 1 occurs; and so on Histogram equalization is one of the well known image enhancement technique. It became a popular technique for contrast enhancement because this method is simple and effective. The main idea of this method is to remap the grey level of an image this method wants to introduce some annoying artifacts and unnatural enhancement. We want to overcome this limitation different brightness preserving techniques are used which covered in literature survey. Comparative analysis of different enhancement techniques will be carried out. This comparison will be done on the basis of subjective and objective parameters. Subjective parameters are visual quality and computation time and objective parameters are Peak signal to- noise ratio (PSNR), Mean squared error (MSE), Normalized Absolute Error (NAE), Normalized Correlation, Error Color and Composite Peak Signal to noise Ratio (CPSNR) Keywords : Contrast enhancement, Histogram Equalization, PSNR, MSE, NAE, CPSNR, Visual quality 1. INTRODUCTION Histogram based techniques is one of the most important digital image processing techniques which can be used for image enhancement.[1] A familiar example of enhancement is shown in Fig.1 in which when we increase the contrast of an image and filter it looks better One of the benefit of this technique is simplicity of implementation of algorithm. Also this should be mentioned that histogram based technique is much less expensive comparing to other method. Histogram based technique for image enhancement is normally based on equalizing the Histogram of image and increases the dynamic ISSN: 2319-1112 /V1N2: 69-78 IJAEEE
IJAEEE,Volume1,Number 2 Rahul Jaiswal et al. Figure1 (a) Distorted Image, (b) Enhanced Image c) Original Histogram d) Histogram after Equalization Increases the dynamic range corresponding to the image.in general the HE stretching the low contrast Level of image with narrow of histogram. Histogram modeling has been found to be powerful techniques. Out of the five senses sight, hearing, touch, smell and taste which humans use to perceive their environment, sight is the most powerful Receiving and analyzing images forms a large part of the routine cerebral activity of human beings throughout their waking lives. Fact, more than 99% of the activity of the human brain is involved in processing images From the visual cortex. A visual image is rich in information. Confucius said, A picture is worth a thousand words. [2] Image Enhancement is simple and most appealing area among all the digital image processing techniques Image enhancement is to process an image so that the result is the more suitable than the original image for a specific application[3].image enhancement approaches fall into two broad categorirs: spatial domain method and frequency domain methods. [4]
Image Enhancement Techniques Based on Histogram Equalization 71 Input image Determine maximum pixel intensity Select value of gamma Look-up-table formation Mapping of input pixel value to value in look-up table Fig 2 (Flow chart of gamma correction) A grey scale image is an image in which the intensity of all pixel lie in the range [0, L-1] where 0 denotes black and L-1 is white. If there are only two intensity levels in an image it is known as a binary image [4] Gamma Correction A Variety of device used for image capture, printing and display respond according to power law. By convention the exponent in the power law equation is referred to as gamma. The process used to correct this power law response phenomena is called gamma correction. Gamma correction is a factor by which software can correct this non linearity resulting in correctly displayed device. The flow chart for gamma correction through a look-up-table formation is shown in fig. 2.The crucial step is the look-up-table formation and the selection of the gamma value. The formula to create look-up-table [4] Histogram base technique for image enhancement is mostly based on equalizing the histogram of the image and increasing the dynamic range corresponding to image. Histogram Equalization method has disadvantage which effect the efficiency of system. Histogram equalization assign one grey level into two different neighbor gray level with different intensity.[5] If most of an image include a gray level Histogram Equalization (HE) assign a gray level with higher intensity to that gray level and it will cause a phenomena as we called it washed out. II A: Adaptive Histogram Equalization Method This method is the improvement over traditional Histogram Equalization method. It improve the contrast of image by Transforming the value in the intensity image I. unlike HISTEQ it operate on small data region (tiles) rather than the entire image each tiles contrast is enhanced, so that the histogram of the Output region approximately matches
IJAEEE,Volume1,Number 2 Rahul Jaiswal et al. the specified histogram. The neighboring tiles are then combined using bilinear interpolation in order to eliminate artificially induced boundaries. B: Dualistic sub-image histogram equalization method One of the improved histogram based method is Dualistic Sub Image Histogram Equalization (DSIHE). In this method first Histogram is divided to segment based on entropy and then Histogram equalization method is applied on each segment separately This is a novel histogram equalization technique in which theoriginal image is decomposed into two equal area sub-images based on its gray level probability density function. Then the two subimages are equalized respectively. At last, we get the result after the processed sub-images are composed into one image. In fact, the algorithm can not only enhance the image visual information effectively, but also constrain theoriginal image's average luminance from great shift. [5] C. Dynamic histogram equalization for image contrast Enhancement It employs a partitioning operation over the input histogramto chop it into some sub histograms so that they have nodominating component in them. Then each sub-histogram goesthrough HE and is allowed to occupy a specified gray level rangein the enhanced output image. Thus, a better overall contrastenhancement is gained by DHE with controlled dynamic rangeof gray levels and eliminating the possibility of the low histogramcomponents being compressed that may cause some part ofthe image to have washed out appearance. III Implementation Comparing all these techniques on the basis of performance parameters in objective and subjective manner. These are the merits on the bases of that I will compare above defined techniques. The intensity histogram shows how individual brightness level is occupied in an image; the image contrast is measured by the range of brightness level. Histogram plots the number of pixel with a particular brightness level against the brightness level Histogram is a good representation of the contrast, brightness and data distribution [6] A. Contrast Limited Adaptive Histogram Equalization method: 1. Obtain all the inputs: Image, Number of regions in row and Column directions, Number of bins for the histograms used in building image transform function (dynamic range), Clip limit for contrast limiting (normalized from 0 to 1) 2. Pre-process the inputs: Determine real clip limit from the normalized value if necessary, pad the image before splitting it into regions 3. Process each contextual region (tile) thus producing gray Level mappings: Extract a single image region, make a Histogram for this region using the specified number of bins, clip the histogram using clip limit, create mapping for this region 4 Interpolate gray level mapping in order to assemble final CLAHE image: Extract cluster of four neighboring mapping Functions, process image region partly overlapping each Of the mapping tiles, extract a single pixel, apply four Mappings to that pixel, and interpolate between the results to obtain the output pixel; repeat over the entire image.[7]
Image Enhancement Techniques Based on Histogram Equalization 73 Fig 3a) Flow chart of CLAHE B. Dualistic Sub-Image histogram equalization methods Fig3b) Flow chart of DSIHE C. Dynamic histogram equalization for Image contrast enhancement: Contrast defines the difference between lowest and highest Intensity level. Higher the value of contrast means more difference between lowest and highest intensity level. Clip the histogram using clip limit, and create a mapping (Transformation function) for this region
IJAEEE,Volume1,Number 2 Rahul Jaiswal et al. Fig3c)Flow chart for DHE 4. Matrices for Gray Scale Images A Peak-signal-to-noise-ratio (PSNR): PSNR is the evaluation standard of the reconstructed image quality, and is important measurement feature.[8] PSNR is measured in decibels (db) and is given by: Where the value 255 is maximum possible value that can be attained by the image signal. Mean square error (MSE) is Defined as where M*N is the size of the original image Higher the PSNR values is, better the reconstructed image Comparison of Various Parameters for Rice Image
Image Enhancement Techniques Based on Histogram Equalization 75 a) Original Image a) Histogram of Original Image b) CLAHE Image
IJAEEE,Volume1,Number 2 Rahul Jaiswal et al. b) CLAHE Histogram c) DSIHE Image c) DSIHE Histogram
Image Enhancement Techniques Based on Histogram Equalization 77 d)dhe Image d) DHE Histogram B Absolute means brightness error (AMBE) It is the Difference between original and enhanced image and is given as AMBE=E(x)-E(y) Where E(x) = average intensity of input image E(y)=average Intensity of enhanced image C Contrast: Contrast defines the difference between lowest and highest intensity level. Higher the value of more contrast means more difference between lowest and highest intensity level. 5. Results of test image rice Parameter AMBE Contrast PSNR Technique CLAHE 12.85 22.58 0.026 DSIHE 3.908 32.87 0.0312 DHE 12.08 11.14 0.111 Everybody can made comparison of Parameter AMBE for different image enhancement technique. This value should be as small as possible which indicate the difference between original and enhanced image should be minimum. Now consider PSNR, CLAHE gives better output as it is cleared from the formula that PSNR should be as high as possible so that noise content should be lower than signal content. 6. Conclusion In this Paper, a frame work for image enhancement based on prior knowledge on the Histogram Equalization has been presented. Many image enhancement schemes like Contrast limited Adaptive Histogram Equalization
IJAEEE,Volume1,Number 2 Rahul Jaiswal et al. (CLAHE), Equal area dualistic sub-image histogram equalization (DSIHE), Dynamic Histogram equalization (DHE) Algorithm has been implemented and compared. The Performance of all these Methods has been analyzed and a number of Practical experiments of real time images have been presented. From the experimental results, it is found that all the three techniques yields Different aspects for different parameters. In future, for the enhancement purpose more images can be taken from the different application fields so that it becomes clearer that for which application which particular technique is better both for Gray Scale Images and color Images. Optimization of various enhancement techniques can be done to reduce computational complexity as much as possible 7. Reference [1] R.C Gonzalez and R.E Woods Digital Image Processing New Jersey: Prentice-Hall, Inc., 2001 [2] S.Lau, Global image enhancement using local information, Electronics Letters, vol. 30, pp. 122 123, Jan. 1994. [3] Akansha Singh and K.K Singh Digital Image ProcessingUmesh Publication First Edition 2011. [4] J. Zimmerman, S. Pizer, E. Staab, E. Perry, W. McCartney, B. Brenton, Evaluation of the effectiveness of adaptive histogram equalization for contrast enhancement, IEEE Transactions on Medical Imaging, pp. 304-312, 1988. [5] Rajesh Garg, Bhawana Mittal, SheetalGarg HistogramEqualization Technique For Image Enhancement IJECT Vol.2, Issue1, March 2011 [6] Yu Wan, Qian Chen, Bao-Min Zhang, Image enhancement based on equal area dualistic sub-image histogram equalization method, IEEE Transactions Consumer Electron., vol. 45, no. 1, pp. 68-75, 1999. [7] Yeong-Taeg Kim, Contrast enhancement using brightness preserving bi-histogram equalization, IEEE Trans. Consumer Electronics, vol. 43, no. 1, pp. 1-8, 1997. [8] M. Abdullah-Al-Wadud, Md. HasanulKabir, M. Ali AkberDewan, OksamChae, A dynamic histogram equalizationfor image contrast enhancement, IEEE Transactions.Consumer Electron., vol. 53, no. 2, pp. 593-600, May2007. [9] K. Wongsritong, K. Kittayaruasiriwat, F. Cheevasuvit,K. Dejhan, A. Somboonkaew, Contrast enhancementusing multipeak histogram equalization with brightnesspreserving, Circuit and System, 1998, IEEE APCCAS1998. The 1998 IEEE Asia-Pacific Conference on 24-27Nov. 1998, pp. 455-458, 1998. [10] Y. Wang, Q. Chen, B. Zhang, Soong-Der Chen, and Abd. RahmanRamli, Minimum mean brightness error bihistogramequalization in contrast enhancement, IEEETransactions Consumer Electron. vol. 49, no. 4, pp. 1310-1319, Nov. 2003.