Image Denoising Using Patch Based Processing With Fuzzy Triangular Membership Function
In this paper image denoising method based on fuzzy triangular membership function. For a given corrupted image, at first I converted to the fuzzy values using the fuzzification method. Then, I extract all patches with overlaps, after extracting all patches each patch is to be permuted and apply the fuzzy triangular membership function. I extract all patches with overlaps, refer to these as coordinates in high-dimensional space, and arrange them such that they are chained in the “shortest possible path,” basically solving the traveling salesman problem. The obtained ordering I am applying the fuzzy defuzzification method to convert fuzzy value to the crisp values, to what should be a regular signal. This enables us to get good recovery of the clean image by applying comparatively simple one-dimensional smoothing operations (such as filtering or interpolation) to the reordered set of pixels. The performance of this approach is experimentally verified on a variety of images and noise levels. The results presented here demonstrate that proposed method is on par or exceeding the current state of the art, both visually and quantitatively.
Keywords: Patch-based processing, fuzzification, defuzzification, triangular membership function, traveling salesman, pixel permutation, denoising.
Download Full-Text
ABOUT THE AUTHOR
Krishan Kundu
Krishan Kundu received B.Tech from Kalyani Govt. Engineering College, Kalyani, Nadia, WB, India and M.Tech from WBUT, Kolkata, India in Computer Science & Engineering. Presently, he is a Assistant Professor in Computer Science & Engineering Department at Govt. college of Engineering & Textile Technology, Serampore, Hooghly, India. He is currently pursuing his Ph. D in Computer Science. His research area is image denoisy.
Krishan Kundu
Krishan Kundu received B.Tech from Kalyani Govt. Engineering College, Kalyani, Nadia, WB, India and M.Tech from WBUT, Kolkata, India in Computer Science & Engineering. Presently, he is a Assistant Professor in Computer Science & Engineering Department at Govt. college of Engineering & Textile Technology, Serampore, Hooghly, India. He is currently pursuing his Ph. D in Computer Science. His research area is image denoisy.