Analysis of various Fuzzy Based image enhancement techniques SONALI TALWAR Research Scholar Deptt.of Computer Science DAVIET, Jalandhar(Pb.), India sonalitalwar91@gmail.com RAJESH KOCHHER Assistant Professor Deptt. of Information Technology DAVIET, Jalandhar(Pb.), India rajesh.kochher@gmail.com Abstract: Fuzzy logic is a multivalent logic that is used to deal with the uncertainty and imprecision. Various fuzzy based methods have been developed for image enhancement. Fuzzy IF THEN rules, Fuzzy based reasoning and Fuzzy inference system etc have been utilised in different ways to enhance the quality of images, remove the noise and improve the contrast of the images. This paper has discussed various kind of fuzzy based enhancement techniques. This paper has also discussed advantages and limitations of various fuzzy based enhancement techniques Keywords: Fuzzy logic, Fuzzy enhancement. 1. Introduction: Fuzzy logic provides a good mathematical framework to deal with the uncertainity of information. Fuzzy set theory provides a capability to characterize the ambiguity and imprecision and to incorporate human knowledge into problem-solving process[1] Fuzzy is a powerful tool to knowledge representation and process human knowledge in form of fuzzy if then rules. Fuzzy techniques are used to deal with uncertainty and vagueness. Fuzzy logic is flexible. With any given system, it s easy to manage it. Fuzzy logic is conceptually easy to understand. Figure 1 Fuzzy image processing[11] Fuzzy image processing has three main stages : Image fuzzification, modification of membership values and if necessary,if image defuzzification. Therefore, the coding of image data(fuzzification)and decoding of results (defuzzification) are steps that makes possible to process images with fuzzy techniques.main power of fuzzy image processing is in the middle step (Membership modification).the main contribution of fuzzy logic in the field of image enhancement using the fuzzy framework have been established in recent years. The first contribution deals with basic 9
fuzzy rules for image enhancement where in a set of neighbourhood pixels form the antecedent and consequent clauses that serve as a fuzzy rule for the pixel to be enhanced. The second contribution relates with rule based smoothing in which different filter classes are devised on the basis of compatibility with the neighbourhood[8]. 2. Literature Survey: H.D. Cheng, Huijuan Xu (2000)[1] found that Fuzzy set theory is a useful tool for handling the uncertainty in the images associated with vagueness and/or imprecision. It presented a novel adaptive direct fuzzy contrast enhancement method based on the fuzzy entropy principle and fuzzy set theory. The experimental results have demonstrated that the proposed algorithm is more adaptive and elective for contrast enhancement. Moreover, it significantly reduces the overenhancement/under-enhancement due to its better adaptive capability. M. Hanmandlu, Devendra Jha, R.Sharma (2003) [2] presented a Gaussian membership function that transforms the saturation and intensity histograms of HSV color model into the fuzzy domain. It introduced a new contrast intensification operator called NINT, which involves a parameter t for enhancement of color images. By minimizing the fuzzy entropy of the image information, the parameter t is calculated globally.. The fuzzifier and intensification parameters are evaluated automatically for the input color image, by optimizing the contrast and entropy in the fuzzy domain. The intensification operation leads to enhancement by improving the fuzzy homogeneity of the pixel about the crossover point. A visible improvement in the image quality for human contrast perception is observed, also demonstrated here by the reduction in index of fuzziness and entropy of the output image. Nachiket Desai et al.( 2009) [3] presented a novel fuzzy logic based algorithm to de-weather fog degraded images. Airlight is estimated using fuzzy logic followed by color correction for enhanced visibility. The algorithm works efficiently for images with a sky region. The limitations of the algorithm is that algorithm cannot decide if an image needs de-weathering requiring human intervention to start/stop deweathering process. Khairunnisa Hasikin Nor Ashidi Mat Isa (2012) [4]presented a novel enhancement technique based on fuzzy set theory. The new enhancement approach considers poor contrast and nonuniform illumination problems that often occur in a recorded image. A new parameter, called the contrast factor, is proposed based on differences in the graylevel values of pixels in the local neighborhood.. The contrast factor is measured by both local and global information to ensure that the fine details of the degraded image are enhanced. This parameter is used to divide the degraded image into bright and dark regions. The enhancement process is applied on grayscale images wherein the modified Gaussian membership function is employed. The process is performed separately according to the image s respective regions. Improved image quality is obtained, and the proposed method is able to preserve the details and the mean luminance of the image.. The proposed method is better in preserving brightness, better contrast and detail preservation. FHE is the fastest to be executed because the image is treated as a mixed region in which overexposed and underexposed regions are not considered.. Nutan Y.Suple, Sudhir M. Kharad (2013) [5] presented the design of the technique using fuzzy inference system for contrast enhancement. It has three main stages, namely, image fuzzification, modification of member ship function values, and 10
defuzzification. Fuzzy image enhancement is based on gray level mapping into membership function. The focus is to generate an image of higher contrast than the original image by giving a larger weight to the gray levels that are closer to the mean gray level of the image than that are farther from the mean.. Fuzzy Image Enhancement treats image as fuzzy set and operates on those sets.v. Magudeeswaran and C. G. Ravichandran(2013)[6] presented Fuzzy Histogram Equalization for image contrast enhancement. First, fuzzy histogram is computed based on fuzzy set theory to handle the inexactness of gray level values in a better way compared to classical crisp histograms Second, the fuzzy histogram is separated into two based on the median value of the original image. Finally, the FHE approach is applied independently on each sub histogram to improve the contrast. The proposed FHE method does not only preserve image brightness but also improves the local contrast of the original image then equalizes them independently to preserve image brightness. The proposed method can effectively and significantly eliminate washed-out appearance and adverse artifacts induced by several existing methods. A. Alajarmeh et. al (2014)[7] presented a novel technique for enhancing haze plaqued video captured during rain,for and haze conditions. This paper proposed the combination of dark channel and fuzzy logic based on stable atmospheric scattering model to improve the visibility of video frames and making them haze free high quality.the technique works as firstly hazy video is capured or acquired,then Fog effect map is estimated,then airlight is estimated and finally fuzzy logic rules and membership functions are used to enhance the scene luminance. G. Raju and Madhu S. Nair (2014) [8] proposed a novel fuzzy logic and histogram based algorithm for enhancing low contrast color images. This approach is mainly based in two important parameters M and K where M is the average intensity value of the image and K is contrast intensification parameter. The presented fuzzy enhancement approach uses HSV color space where only V component is stretched by preserving the chromatic information such as hue(h) and Saturation (S). The approach is computationally fast and improves the visual quality of the images. The limitation of the approach is it can be only applied to low contrast and low bright color images. Sohail Masood et al. (2014) [9] proposed a color difference based fuzzy filter for fix and random-valued impulse noise. Noise detection is done to detect noisy pixel. An improved Histogram based Fuzzy Color Filter(HFC)is presented for noise removal. Multiple fuzzy membership functions are used so that the best suitable membership function for local image statistics can be used automatically. The proposed approach work well for salt and pepper noise and uniform impulse noise. Jonathan Cepeda-Negrete and Raul E. Sanchez Yanez (2014)[10] presented a novel framework for automatic selection system to choose the best color constancy algorithm for the enhancement of dark images. This work focuses on color constancy and image color enhancement. Three algorithms used in the presented work : The White Patch, The Gray World and The Gray Edge. These algorithms have been considered because of their accurate remotion of illuminant and showing outstanding color enhancement on images. The presented work developed a fuzzy rule based system to model the rules. A training protocol has been used to determine fuzzy rules according to features computed from a subset of training images. For a given test image the best algorithm was chosen according to rule evaluation. 3. Gaps in Literature 11
The fuzzy based enhancement techniques have neglected the following issues: 1. The idea of adaptivity of dark channel has been neglected by most of the existing techniques. 2. The problem of uneven illumination is not sorted to a great extent. 3. Effect of artficial lighting needs to be considered in enhancement techniques. 4. Conclusion This paper discussed the various fuzzy based enhancement techniques that have utilised the fuzzy logic ability to deal with vagueness or uncertainity. Fuzzy logic techniques also deal with the multivalent logic to enhance the images. Fuzzy IF THEN rules, fuzzy rule based reasoning, fuzzy based smoothing are the different ways in which fuzzy logic can be used for image enhancement. Due to use of fuzzy logic s multivalent logic ability, different fuzzy techniques have been discussed for enhancing the images improve the quality of the images, reduce the noise and improve the overall contrast. REFERENCES [1] H.D Cheng, and H. Xu. "A novel fuzzy logic approach to contrast enhancement." Pattern Recognition 33, no. 5,pp. 809-819,2000. [2] M. Hanmandlu, Devendra Jha, and R. Sharma. "Color image enhancement by fuzzy intensification." Pattern Recognition Letters 24, no. 1,pp.81-87,2003. [3] N. Desai et al. "A Fuzzy Logic Based Approach to De-Weather Fog-Degraded Images." In IEEE Sixth International Conference on Computer Graphics, Imaging and Visualization, pp. 383-387, 2009. [4]K.Hasikin and N.A. M. Isa. "Enhancement of the low contrast image using fuzzy set theory." In IEEE 14th International Conference on Computer Modelling and Simulation, pp. 371-376, 2012. [5] Suple, Nutan Y., and Sudhir M. Kharad. "Basic approach to image contrast enhancement with fuzzy inference system." International Journal of Scientific and Research Publications 3, no. 6, 2013. [6] V Magudeeswaran, and C. G. Ravichandran. "Fuzzy logic-based histogram equalization for image contrast enhancement." Mathematical Problems in Engineering,2013. [7] A. Alajarmeh,et al. "Real-time video enhancement for various weather conditions using dark channel and fuzzy logic." In IEEE International Conference on Computer and Information Sciences (ICCOINS), pp. 1-6, 2014. [8] G. Raju and M. S. Nair. "A fast and efficient color image enhancement method based on fuzzy-logic and histogram." AEU- 12
International Journal of Electronics and Communications 68, no. 3, pp. 237-243, 2014. [9] S. Masood et al. "Color differences based fuzzy filter for extremely corrupted color images." Applied Soft Computing 21, pp. 107-118, 2014. [10] Cepeda-Negrete, Jonathan, and Raul E. Sanchez-Yanez. "Automatic selection of color constancy algorithms for dark image enhancement by fuzzy rule-based reasoning." Applied Soft Computing,28, pp.1-10,2015. [11]http://neuron.csie.ntust.edu.tw/homewor k/93/fuzzy/%e6%97%a5%e9%96%93%e 9%83%A8/homework_2/M9309001/FIP.file s/image002.gif 13