Fuzzy rule based Contrast Enhancement for Sports Applications

Fuzzy rule based Contrast Enhancement for Sports Applications R.Manikandan 1, R.Ramakrishnan 2 Abstract Sports video and imaging systems are generally affected by poor illumination due to smoke, haze, rain, etc. This poor illumination severely reduces the contrast of the images. Contrast plays a vital role in determining the quality of any image. It is very important, to enhancing the contrast of sports images, since it is difficult to analyze the performance of the player or a team with a poor quality image. Our aim is to develop a contrast enhancement technique to improve the quality of sports image with poor illumination. In our proposed method, the conventional and fuzzy based histogram equalization techniques are used as a contrast enhancement technique. Several methods are available for gray scale image processing whereas dealing with color images is a complicated one. In this process, RGB color planes are used and the results are found to be satisfactory. Keywords: Contrast Enhancement, Fuzzy Logic, Histogram Equalization, Measure of Contrast I. INTRODUCTION In recent days, the sports video and image processing is an interesting research area, since many applications are emerging in this field. The various applications include ball/player tracking, tactics analysis, computer assisted referee, gait analysis, etc. Coaches and athletes are using this medium to measure and to make corrections, and also to analyze the performance of a team and individuals. For this analysis, the quality of the sports images depends on its contrast. Dynamic range determines the contrast of a sport image, which is defined as the ratio between the brightest and the darkest pixel intensities. Higher contrast images usually score higher in visual quality. Images captured in poor or non uniform lighting or with a sensor of small dynamic range results in low contrast images. The quality of such images can be improved by means of using a proper image enhancement technique. In almost all the video processing applications, the first step is to enhance the raw image. Enhancing the contrast of images requires more importance. The aim of contrast enhancement process is to adjust the local contrast in different regions of the image so that the details in dark or bright regions are brought out and revealed to the human viewers. Contract enhancement is usually applied to input Manuscript received Oct, 2013. R.Manikandan, Research Scholar, Department of Advanced Sports Training and Technology, Tamilnadu Physical Education and Sports University, Chennai, India. Mobile No: 9444007821, images to obtain a superior visual representation of the image by transforming original pixel values using a transform function of the form [5]. g(x, y) = T[r(x, y)] where, g(x, y) and r(x, y) are the output and input pixel values at image position. Usually for correct enhancement it is desirable to impose certain restrictions on the transformation function T [1, 2]. The existing techniques of contrast enhancement techniques can be broadly categorized into two groups: direct methods [10, 11] and indirect methods [3, 12-16]. Direct methods define a contrast measure and try to improve it. Indirect methods, on the other hand, improve the contrast through exploiting the under-utilized regions of the dynamic range without defining a specific contrast term. In fact, there are other type of algorithm for contrast enhancement, such as gamma enhancement, power-low rule, logarithmic approach, automatic gain/offset, and transform enhancement. In this paper, the conventional histogram equalization (HE) and fuzzy rule based contrast enhancement are discussed. The paper is organized as follows: Contrast Enhancement Using Histogram Equalization can be found in Section II. The Contrast Enhancement Using Fuzzy Rule is discussed in section III. The discussions and conclusions are presented in sections IV. II. CONTRAST ENHANCEMENT USING HISTOGRAM EQUALIZATION A. Image Histogram In general, a histogram is the estimation of the probability distribution of a particular type of data. An image histogram is a type of histogram which offers a graphical representation of the tonal distribution of the gray values in a digital image. By viewing the image s histogram, we can analyze the frequency of appearance of the different gray levels contained in the image [17]. The fig. 1 below shows an image with its histogram representation. The pixels in the image have a wide histogram representation indicating that the image is of a high quality. A good histogram is that which covers all the possible values in the gray scale used. This type of histogram suggests that the image has good contrast and that details in the image may be observed more easily. R.Ramakrishnan, Professor and Head, Department of Advanced Sports Training and Technology, Tamilnadu Physical Education and Sports University, Chennai, India. Mobile No: 9444048854, 690

C. Histogram equalization Histogram Equalization [4] is a technique that generates a gray map which changes the histogram of an image and redistributing all pixels values to be as close as possible to a user specified desired histogram. HE allows for areas of lower local contrast to gain a higher contrast. Histogram equalization automatically determines a transformation function seeking to produce an output image with a uniform Histogram. Histogram equalization is a method in image processing of contrast adjustment using the image histogram. This method usually increases the global contrast of many a). Original Image images, especially when the usable data of the image is represented by close contrast values. Through this adjustment, the intensities can be better distributed on the histogram. Histogram equalization accomplishes this by effectively spreading out the most frequent intensity values. Histogram equalization automatically determines a transformation function seeking to produce an output image with a uniform Histogram. Let X={X(i,j)} denotes a image composed of L discrete gray levels denotes as X={x 0, x 1,---,x L-1 } b). Histogram of the Image Fig. 1 A colored image with Histogram representation B. Histogram Processing The Histogram [17] of digital image with the intensity levels in the range [0, L-1] is a discrete function. Where h(r k ) = n k r k is the intensity value. n k is the number of pixels in the image with intensity r k h(r k ) is the histogram of the digital image with Gray Level r k Histograms are frequently normalized by the total number of pixels in the image. Assuming a M N image, a normalized histogram. P (r k ) = n k, k = 0,1,2,3,, L 1 MN is related to probability of occurrence of r k in the image. P (r k ) gives an estimate of the probability of occurrence of gray level r k. The Sum of all components of a normalized histogram is equal to1. The histogram of bad images is usually narrow while that of good images are wide. To change a bad image to a good one, the histogram is thus modified. For a given image x, the probability density function P (x k ). n k P (x k ) = n K = 0,1,...,L-1, n k represents the number of times that the level x k appears in the input image X, n is the total number of samples in the input image, P(x k ) is associated with the histogram of the input image which represents the number of pixels that have a specific intensity. Based on the probability density function, the cumulative density function is defined as k C(x) = j =0 p(x j ) x k = x for k=0,1,---,(l-1) and C (x L-1 ) by definition. HE is a scheme that maps the input image into the entire dynamic range (x 0, x L-1 ) by using the cumulative density function as a transform function. A transform function f(x) based on the cumulative density function defined as f(x) = x 0 + (x L-1 - x 0 ) C(x) Then the output image of the HE, Y={Y(i,j)}can be expressed as Y = f(x) = f{x (i, j)/ X(i, j) X} Based on information theory, entropy of message source will get the maximum value when the message has uniform distribution property. 691

a) Original Image Img 1 on the low side of the gray scale resulting in a dark image. Fig. 2c) shows the enhanced image obtained using histogram equalization and 2d) shows the corresponding histogram of the enhanced image. From the histogram it is clear that the components of the histogram cover a wide range of gray scale and the distribution is nearly uniform. The advantages of the HE include (i) it suffers from the problem of being poorly suited for retaining local detail due to its global treatment of the image. (ii) Small-scale details that are often associated with the small bins of the histogram are eliminated. The disadvantage is that it is not a suitable property in some applications such as consumer electronic products, where brightness preservation is necessary to avoid annoying artifacts. The equalization result is usually an undesired loss of visual data, of quality, and of intensity scale. b) Histogram Original Image Img 1 c) Enhanced Image Img 1 d) Histogram of the Enhanced Image Img 1 Fig. 2 Contrast Enhancement using Histogram Equalization Fig. 2 shows the results obtained using histogram equalization. Fig. 2a) shows the original image and 2b) shows the histogram of the original image. From the histogram it is clear that the components of the histogram are concentrated III. CONTRAST ENHANCEMENT USING FUZZY RULE Fuzzy logic has rapidly become one of the most successful technologies for developing sophisticated control systems. The foundation of fuzzy set theory was first established in 1965 by Lotfi Zadeh. The theory of fuzzy sets is a theory of graded concepts, a theory in which everything is a matter of degree [6]. Unlike two-valued Boolean logic, fuzzy logic is based on degrees of membership and degrees of truth. Fuzzy logic not only recognizes true and false values but is also useful for propositions that can be represented with varying degrees of truth and falseness. Thus Fuzzy logic has filled an important gap in engineering design methods left vacant by purely mathematical approaches (e.g. linear control design) and purely logic-based approaches (e.g. expert systems) in system design [8, 9]. A simple fuzzy system can be explained as follows, 1. First the various inputs of the process is analyzed and the anticipated range of each of the inputs is divided into several coarse, overlapping functions known as Membership Functions or Classes or Fuzzy Sets. 2. Similarly a set of Output Membership Functions is defined covering the range of each output. 3. Every possible combination of input membership classes is related to an output class via a set of logic sentences. Fuzzy Rules take the general form of IF and THEN statement. The process of generating this rule base is called Implication. 4. An appropriate method for establishing the degree of truth of an output membership function based on the relative degree of truth of each of the input functions mapped to it by the fuzzy rules is decided. This is called the Conjunction Method. 5. An appropriate method is further decided for mapping output membership functions, each with a certain degree of truth, back to the input variables. This process is called Defuzzification. To enhance the contrast of sports image using fuzzy logic, Takagi-Sugeno fuzzy rule based system is used. Takagi-Sugeno rules have consequents (THEN outcomes) that are numeric functions (generally linear combinations) of the input values. Algorithm: The algorithm used to enhance the contrast of color image is Step 1. Extract the Red, Green and Blue planes of the color image Step 2. For each plane execute the following steps 692

IF a pixel is dark, THEN make it darker IF a pixel is gray, THEN make it mid-gray IF a pixel is bright, THEN make it brighter Step 3. Concatenate the enhanced Red, Green and Blue planes to obtain the contrast enhanced image. The input membership functions for an image contrast enhancement system are shown below in Fig. 3. Here, the set of all possible input image pixel values is mapped to three linguistic terms: Dark, Gray and Bright. The values μi(z) quantify the degree of membership of a particular input pixel intensity value to the each of the three member functions (Dark, Gray or Bright; denoted by the subscript i). Thus, μdark(z) assigns a value between 0 and 1 to how truly dark a given input pixel intensity value (z) is Similarly, μgray(z) and μbright(z) characterize how truly Gray or Bright a pixel value z is. µ dark z i + µ gray z i + µ brig ht z i refers to the input membership function V d, V g, V b refers to the output membership function This relationship accomplishes the processes of implication, aggregation and defuzzification together with a straightforward numeric computation. Using a Takagi-Sugeno design with singleton output membership functions reduces computational time significantly by simplifying the computational time requirements in implication, aggregation and defuzzification. Figure 4a) shows the original image Img-2 and 4b) shows the enhanced image obtained using fuzzy rule based contrast enhancement. a) original image Img-2 a) Input Membership Function b) Enhanced image Img-2 using fuzzy rule Fig. 4 Contrast Enhancement using Fuzzy Rule b) Output Membership Function Fig. 3 Input and Output Membership Function for Fuzzy Rule Based Contrast Enhancement The output member functions are referred to as Darker, Mid-gray and Brighter. The output fuzzy sets are defined as fuzzy singletons - that is the output membership functions are single-valued constants. For our application the singleton output membership function values have been selected as follows: Darker = 0 (V d ) Mid-gray = 127 (V g ) Brighter = 255 (V b ) The output V o to any input z i is given by, V o = [µ dark z i V d + µ gray z i V g + µ brig ht z i V b ] µ dark z i + µ gray z i + µ brig ht z i IV. DISCUSSIONS AND CONCLUSIONS Contrast by definition, is a psychophysical non-measurable characteristic [8]. On the other hand, de-facto, it is a quantitative parameter essential for digital image processing and algorithm developers have to use some formula for Contrast measure. There is no conventional measure for contrast, however to evaluate the contrast enhancement performance of our method, we have considered the following evaluation parameter discussed in [7]. Measure of Contrast = M en M in M in M en - is the average intensity value of the enhanced image M in - is the average intensity value of the original input image Several sports images are taken for the purpose of experimentation and the contrast enhanced results are obtained using the methods described above. Histogram Equalization method though it has shown better measure of contrast than fuzzy rule based method for some of the images, it is seldom used because of the disadvantages discussed earlier. The measure of contrast obtained for a sample of 5 693

test images is shown in table 1 and is also plotted in the graph shown in fig. 5. From the table and the graph it is clear that the measure of contrast is high for the fuzzy rule base method compared with Histogram Equalization. A very high Measure of Contrast is obtained for the fuzzy rule base method. Thus of the two methods proposed contrast enhancement using fuzzy rule base method shows good results and can be used as an effective method for contrast enhancement of color images. Fig. 5 A plot of Measure of Contrast for various images Table 1. Measure of Contrast Contrast Enhancement of the color sports image is the first step in our process of analyzing the sports images to determine the performance of the players. Edge detection techniques are being explored for the next stage of analyzing the images. ACKNOWLEDGEMENT We thank our Secretary and Correspondent Dr.P.Chinnadurai, Panimalar Engineering College, Chennai, India for providing financial assistance and facilities for doing this research. REFERENCES [1] S. Walid and A. Ibrahim, Real time video sharpness enhancement by wavelet-based luminance transient improvement, Proc. of the 9th International Symposium on Signal Processing and Its Applications, pp. 1-4, 2007. [4] Komal vij, Yaduvir singh, Enhancement of images using histogram processing techniques, International Journal of Computer Technology and Applications, vol. 2(2), pp. 309 313, ISSN: 2229-6093. [5] Rafael C.Gonzalez et al, Digital Image Processing, 2nd Ed, PHI. [6] Zadeh, L. A. Fuzzy Sets, Information and Control, vol. 8, 1965, pp. 338-353. [7] Srinivasan,S, Adaptive Histogram-Based Video Contrast Enhancement, Patent Filing, 2005 [8] P.Kannan, S.Deepa, R.Ramakrishnan, Contrast enhancement of sports images using two comparative approaches, vol. 2(6), pp: 141 147, 2012. [9] P. Camelia, A. Vlaicu, M. Gordan and B. Orza, Fuzzy contrast enhancement for images in the compressed domain, Proc. of the International Multi-Conference on Computer Science and Information Technology, pp. 161-170, 2007. [10] S. D. Chen and A. R. Ramli, Minimum mean brightness error bihistogram equalization in contrast enhancement, IEEE Trans. Consumer Electronic, vol. 49, no. 4, pp. 1310-1319, 2003. [11] X. Dong, Y. Pang and J.Wen, Fast efficient algorithm for enhancement of low lighting video, Proc. of the 37th International Conference and Exhibition on Computer Graphics and Interactive Techniques, 2010. [12] S. Du and R. K.Ward, Adaptive region-based image enhancement method for robust face recognition under variable illumination conditions, IEEE Trans. Circuits and Systems for Video Technology, vol.99, pp. 1-12, 2010. [13] A. A. Wadud, M. Kabir, M. H. Dewan and M. C. Oksam, A dynamic histogram equalization for image contrast enhancement, IEEE Trans. Consumer Electronic, vol. 53, no. 2, pp. 593-600, 2007. [14] J. A. Stark, Adaptive image contrast enhancement using generalizations of histogram equalization, IEEE Trans. Image Processing, vol. 9, no. 5, pp. 889-896, 2000. [15] A. Polesel, G. Ramponi and V. J. Mathews, Image enhancement via adaptive unsharp masking, IEEE Trans. Image Processing, vol. 9, no. 3, pp. 505-510, 2000. [16] J. Y. Kim, L. S. Kim and S. H. Hwang, An advanced contrast enhancement using partially overlapped sub block histogram equalization, IEEE Trans. Circuits and Systems for Video Technology, vol. 11, no. 4, pp. 475-484, 2001. [17] R. Krutsch, & D. Tenorio, Histogram Equalization, Freescale Semiconductor, Document Number AN4318, Application Note. R.Manikandan received B.E degree in Electronics and Instrumentation Engineering from Annamalai University, Chidambaram in the Year 2002. He obtained his M.E degree in Applied Electronics from Anna University, Chennai. Currently, he is pursuing PhD in the Department of Advanced Sports Training and Technology at Tamilnadu Physical Education and Sports University, Chennai. His research areas are Image/Video Processing based measurements and Sensors & Transducers. He is working as Associate Professor in the Department of Electronics and Instrumentation Engineering at Panimalar Engineering College, Chennai. He has published research papers in national and international journals and conferences. Dr.R.RAMAKRISHNAN received AMIE degree in Mechanical Engineering from the Institution of Engineers (India), Calcutta. He obtained his M.E degree in Mechanical Engineering from Bharathiar University and PhD degree from Anna University, Chennai. He is working as Professor and Head in the Department of Advanced Sports Training and Technology, Tamilnadu Physical Education and Sports University, Chennai. He worked as Principal, Panimalar Engineering College, Chennai, for two years. His areas of interest are metal cutting, micro machining, modeling and optimization and nano materials. Currently he is guiding six PhD scholars. He has published more than 40 papers in various national and international journals and conferences. [2] Yunbo Rao, Leiting Chen, A survey of video enhancement techniques, Journal of Information Hiding and Multimedia Signal Processing, vol. 3, no. 1, pp. 71-99, Jan 2012. [3] YunBo Rao and Leiting Chen, An efficient contourlet transform-based algorithm for video enhancement, Journal of Information Hiding and Multimedia Signal Processing, vol. 2, no. 3, pp. 282-293, 2011. 694