퍼지연상메모리를 이용한 잡음 내성 이미지 복원

다국어 초록 (Multilingual Abstract)

In this paper, an improved FAM is proposed by adopting similarity learning in the existing FAM(Fuzzy Associative Memory) used in image restoration. Image restoration refers to the recovery of the latent clean image from its noise-corrupted version. In serious application like face recognition, this process should be noise-tolerant, robust, fast, and scalable. The existing FAM is a simple single layered neural network that can be applied to this domain with its robust fuzzy control but has low capacity problem in real world applications. That similarity measure is implied to the connection strength of the FAM structure to minimize the root mean square error between the recovered and the original image. The efficacy of the proposed algorithm is verified with significant low error magnitude from random noise in our experiment.

참고문헌 (Reference)

1 김광백, "퍼지 소속 함수를 이용한 개선된 이진화 방법" 한국컴퓨터정보학회 10 (10): 67-72, 2005

2 B. Kosko, "Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence" Prentice Hall 1992

3 M. T. Hagan, "Neural Network Design" PWS Publishing Company 1996

4 T. Yamaguchi, "Intention Recognition Using Case-Base Learning in Human Vehicle" 110-113, 2003

5 The Duy Bui, "Improving learning rule for fuzzy associative memory with combination of content and association" Elsevier BV 149 : 59-64, 2015

6 Peter Sussner, "Implicative Fuzzy Associative Memories" Institute of Electrical and Electronics Engineers (IEEE) 14 (14): 793-807, 2006

7 K. B. Kim, "Facial Image Denoising from Degraded Rough Casual Photographs using Hopfield Neural Network" International Information Institute (Tokyo) 20 (20): 2513-2518, 2017

8 G Tanaka, "Complex-valued multistate associative memory with nonlinear multilevel functions for gray-level image reconstruction" 20 (20): 1463-1473, 2009