Image Enhancement Using Fuzzy Morphology

Image Enhancement Using Fuzzy Morphology Dillip Ranjan Nayak, Assistant Professor, Department of CSE, GCEK Bhwanipatna, Odissa, India Ashutosh Bhoi, Lecturer, Department of CSE, GCEK Bhawanipatna, Odissa, India Abstract In the present work, fuzzy sets and fuzzy logic along with mathematical morphological operations have been used to enhance the contrast of images A modified membership function has been used to fuzzify the image matrix The generated images in the fuzzy sets method are compared with that of mathematical morphological method The quality of the obtained images in the fuzzy method are observed to be greatly enhanced fostering the view that fuzzy method can be more useful than any other common method of image enhancement Keywords: Fuzzy, enhancement, morphology 1 Introduction Image enhancement plays a fundamental role in many image processing applications where human beings make subjective decisions basing on image information Image enhancement techniques selectively emphasize and inhibit certain information in an image so as to strengthen the usability of the image Image enhancement does not increase the intrinsic information in the original image, but is beneficial to further image applications, such as facilitating image segmentation, or enforcing the capability of human or machine recognition systems to recognize and interpret useful information in the image Image enhancement can be treated as transforming one image to another so that the look and feel of an image can be improved for machine analysis or visual perception of human beings [1] Image Enhancement alters an image to makes its meaning clearer to human observers It is often used to increase the contrast in images that are substantially dark or light Enhancement of noisy image data is a very challenging issue in research and application fields One of the most widely used algorithms for image enhancement is global histogram equalization [2], which adjusts the intensity histogram to approximate a uniform distribution The main disadvantage of global histogram equalization is that the global image properties may not be appropriately applied in a local context In fact, global histogram modification treats all regions of the image equally and therefore, often yields poor local performance in terms of detail preservation Global stretching and histogram equalization techniques do not always produce good results, especially for images with large spatial variation in contrast In order to address the problem, a good number of local contrast enhancement methods have been proposed These techniques can be divided into three broad categories: (a) Spatial (multi-scale) domain methods, which operate directly on pixels (b) Frequency (multi-resolution) domain methods, which operate on the Fourier transform of an image (c) Fuzzy domain methods, which involves the use of knowledge-base systems that are capable of mimicking the behavior of a human expert Fuzzy logic provides a good mathematical framework to deal with uncertainty of information [3] A gray tone picture possesses inherent vagueness and ambiguity due to variable lighting conditions of the object, the non-linearity of imaging systems, and the subjective evaluation of image quality by human beings This is why fuzzy set theory is introduced into image processing Fuzzy set theory provides a capability to characterize the uncertainty and imprecision and to incorporate human knowledge into problem-solving process [4-7] Fuzzy image processing is the collection of all approaches that understand, represent and process the images, their segments and features as fuzzy sets In the last few years, nonlinear filters based on fuzzy models have been shown to be very effective in removing noise without destroying the useful information contained in the image data [8] In the present work, fuzzy morphological image processing is described Based on the mathematical morphology rules, fuzzy sets and fuzzy logic theorem, fuzzy morphology operations are defined In general, mathematical morphology operation definitions have similar structures as that of set theory and set operations definitions For this reason fuzzy set theory is easily applied to the mathematical morphology Since the gray scale images are discrete structures having 1 and 0 sets, fuzzification process can be a good application for transforming the discrete set to the fuzzy set In the present study, a gray scale image is fuzzified with modified membership functions Basic mathematical morphology operations like EROSION, DILATION, OPEN and CLOSE are implemented and inspected via the fuzzy membership functions This method effectively enhances the contrast of image If the observed data are disturbed by random noise then the intensifier operator [9] should convert the image data into the fuzzy domain and process some morphological operation All the implementation work has been done in MATLAB 75 image processing tool box Experimental results show the improvement in the quality of images We have tested the proposed algorithm in cell images and compared our results with that of some existing non fuzzy methods wwwborjournalscom Blue Ocean Research Journals 22

The organization of the paper is as follows Mathematical morphological image processing methods are described in Section 2 and Fuzzy image processing methods are introduced in Section 3 The proposed algorithm is described in Section 4 and we have compared the fuzzy simulation results with that of the non fuzzy methods in Section 5 At the end, conclusions and future prospects of the works are presented in Section 6 2 Morphological Image Processing Morphology is a mathematical framework for the analysis of spatial structures and is based on set theory It is a strong tool for performing many image processing tasks Mathematical morphology is completely based on set theory Morphological sets represent important value By using set operations many useful operators can be defined The important morphological operations are basically dilation, erosion, open and close operations Morphological operations make use of a structuring element M; which can be either a set or a function that corresponds to a neighborhood-function related to the image function g(x) [10] In general, a dilation (denoted by is every operator that commutes with the supremum operation On the other hand, erosion (denoted by ) is every operator that commutes with the infimum operation There is a homomorphism between the image function g and the set B of all pixels with image function value 1 The structuring element M(x) is a function that assigns a subset of N N to every pixel of the image function Then dilation, an increasing transformation, is defined as Whereas, erosion, a decreasing transformation, is defined as In the same manner, opening and closing of set B by structuring element M are respectively defined as B M = ((B, M) M), and B M = ((B M) M) For further details about morphological operations one can refer to [1], [10] and [11] 3 Fuzzy Image Processing Fuzzy image processing has three main stages: image fuzzification, modification of membership values, and, if necessary, image defuzzification The fuzzification and defuzzification steps are due to the fact that we do not possess fuzzy hardware Therefore, the coding of image data (fuzzification) and decoding of the results (defuzzification) are steps that make possible to process images with fuzzy techniques As is evident from Figure 1, the main power of fuzzy image processing is in the middle step (membership modification) [12] After the image data are transformed from gray-level plane to the membership plane (fuzzification), appropriate fuzzy techniques modify the membership values In fuzzy sets, the membership is a matter of a degree, ie, degree of membership of an object in a fuzzy set expresses the degree of compatibility of the Figure 1: Fuzzy Image Processing object with the concept represented by the fuzzy set [13] Each fuzzy set, A is defined in terms of a relevant universal set X by a membership function Membership function assigns each element x of X a number, A(x), in the closed unit interval [0, 1] that characterizes the degree of membership of x in A In defining a membership function, the universal set X is always assumed to be a classical set wwwborjournalscom Blue Ocean Research Journals 23

A gray value image is considered as a fuzzy set in the sense that it is a fuzzy version of a binary image, or that a gray value represents the degree to which pixel belongs to the image foreground 4 Proposed Work On Fuzzy Morphological Image Processing In the present work, we have considered an image of 512 512 dimensions as an array of fuzzy singletons, each with a value of membership denoting the degree of brightness level p, p = 0, 1, 2 255 In order to get the fuzzified matrix, we have used a modified membership function defined by Where The fuzzified image is then operated through different mathematical morphological operators like DILATION, EROSION, OPEN and CLOSE with the structuring element of 3 x 3 mask filter Brighter images are obtained by using the contrast intensification operator INT, on the morphologically operated image The algorithm for the proposed work comprises of the following steps Step1: Read the original image Step2: Fuzzify the input image with the membership function Step3: Apply 3x3 pixel mask window to the image which are a set of fuzzy logic conditions Step4: Perform morphological operation on the fuzzified image Step5: Apply the intensifier operation to modify the membership values 5 Experimental Results and Discussion In the present scheme, fuzzy morphology operations are performed with the help of fuzzy membership functions An original cell image shown in Figure 2, is fuzzified with the proposed fuzzy membership function Then a fuzzy structuring element is traversed on the whole image to process dilation, erosion, open and close operations Structuring element is selected as a 3x3 mask matrices to cover the whole image boundaries We have used a small odd sized structuring element mask for better performance The values used inside the structuring element are the pixel values randomly selected For comparison of the present fuzzy scheme, we have used the non fuzzy mathematical morphological operations of the same image and the generated output images are shown in Figures 3-6 The images generated as a result of the convolution process based on the fuzzy morphological operations, are shown in Figures 7-10 The experimental fuzzy images obtained are brighter and enhanced compared to the Figures3-6 From the generated images, it can be subjectively concluded that fuzzy morphological algorithm works better than other morphological algorithm wwwborjournalscom Blue Ocean Research Journals 24

Figure6: Close image using non Fuzzy scheme Figure7: Fuzzy dilated image Figure8: Fuzzy erosion image wwwborjournalscom Blue Ocean Research Journals 25

Figure9: Fuzzy open image Figure10: Fuzzy close image 6 Conclusions Fuzzy set and fuzzy logic theory is a new research area for defining new algorithms and solutions in mathematical morphology environment Fuzzy morphology approach to image enhancement gives better results than various existing enhancement approaches In the present study, we have used fuzzy morphological methods to enhance the contrast of images The generated images through fuzzy logic have been compared with that of some non fuzzy morphological methods The output images obtained by the use of fuzzy morphological method are observed to be brighter and enhanced The proposed approach can be useful in various applications related to objects identification, geographical surveys, character recognition etc In future, modified algorithm using fuzzy logic and fuzzy sets may produce better results References [1] Serra j Image Analysis and Mathematical Morphology Academic Press, London, 1982 [2] Gonzalez R, Wintz P, Digital Image Processing Reading, MA, Addison Wesley,1987 [3] Timothy J Ross, Fuzzy Logic with Engineering Application 2nd Edition, Wiley, 2004 [4] Farbiz F, Menhaj M B, Motamedi S A, Hagan M T, A New Fuzzy Logic Filter for Image Enhancement, IEEE Transactions on Systems Man, and Cybernetics,2000,Part B, 30(1): 110-119 [5] Tyan C Y, Wang P P Image Processing- Enhancement, Filtering and Edge Detection Using The Fuzzy Logic Approach In Proceedings of the 2nd IEEE Conference on Fuzzy Systems, San Francisco, USA, 1993,PP 600-605 [6] Chen B T, Chen Y S, Hsu W H, Automatic Histogram Specification Based on Fuzzy Set Operations for Image Enhancement IEEE Signal Processing Letters,1995, 2( 2): 37-40 [7] Russo F Recent Advances in Fuzzy Techniques for Image Enhancement IEEE Transactions on Instrumentation and Measuremen,1998,, 4(6): 1428-1434 [8] Chowdhury M,Islam Md, Begum N, Bhuiyan Md Digital image enhancement with fuzzy rule-based filtering Computer and information technology,icct,2007, pp 1-3 [9] Sivanandam S N, Sumathi S, Deepa S N, Introduction to Fuzzy Logic using MATLAB2007, SpringerVerlag Berlin Heidelberg [10] Soille, Morphological Image Analysis: Principles and Application Springer, Berlin,1999 [11] Gonzalez R, Woods R, Eddins S Digital Image Processing Using MATLAB2004,Prentice Hall [12] Tizhoosh, Fuzzy Image Processing,1997, Springer, Berlin [13] Burillo P, Frago N,Fuentes R, Fuzzy Morphological Operators in Image Processing, 2003, Mathware and Soft Computing wwwborjournalscom Blue Ocean Research Journals 26