Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

Noise-tolerant Image Restoration with Similarity-learned Fuzzy Association Memory

  • Received : 2020.02.11
  • Accepted : 2020.03.09
  • Published : 2020.03.31
Download PDF
⟨ Previous Next ⟩

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.

본 논문에서는 이미지 복원에 사용되는 기존의 FAM (Fuzzy Associative Memory)에 유사성 학습을 채택하여 개선된 FAM을 제안한다. 이미지 복원은 노이즈가 존재하는 버전에서 원 이미지에 가깝게 복원하는 것을 의미한다. 얼굴 인식과 같은 중요한 적용 문제에서 이 프로세스는 잡음에 강하고 견고하며 빠르며 확장 가능해야한다. 기존의 FAM 은 강력한 퍼지 제어를 통하여 도메인에 적용 할 수 있지만 실제 응용 프로그램에서는 용량 문제가 있지만 단순한 단일 계층 신경망이다. 유사성 측정은 복구 된 이미지와 원본 이미지 사이의 제곱 평균 오차를 최소화하기 위해 FAM 구조의 연결 강도와 관련이 있다. 제안된 알고리즘의 효과는 실험에서 랜덤 노이즈로 인한 오류 크기가 현저히 낮아지는 것을 확인하였다.

Keywords

References

  1. B. Kosko. "Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence," Prentice Hall. 1992.
  2. M. T. Hagan, H. B. Demuth, M. Beale, "Neural Network Design," PWS Publishing Company, 1996.
  3. T. Yamaguchi, C. Dayang, Y. Takeda J. Jing, "Intention Recognition Using Case-Base Learning in Human Vehicle," In Proceedings of ISIS. pp.110-113, 2003.
  4. P. Sussner, ME Valle. "Implicative fuzzy associative memories," IEEE Transactions on Fuzzy Systems, Vol. 14, No. 6. pp. 793-807, June 2006. DOI: 10.1109/TFUZZ.2006.879968
  5. TH Nong, TK Dang. "Improving learning rule for fuzzy associative memory with combination of content and association," Neurocomputing. Vol. 149, No. Part A, pp 59-64, Feb. 2015. https://doi.org/10.1016/j.neucom.2014.01.063
  6. G Tanaka, K. Aihara. "Complex-valued multistate associative memory with nonlinear multilevel functions for gray-level image reconstruction." IEEE Transactions on Neural Networks. Vol. 20, No. 9, pp 1463-73, Sep. 2009. DOI: 10.1109/IJCNN.2008.4634234
  7. K. B. Kim, Y. J. Kim, "Enhanced Binarization Method using Fuzzy Membership Function," Journal of the Korea Society of Computer and Information , Vol.10, No.1, pp.67-72, March 2005.
  8. K. B. Kim, D. H. Song. "Facial Image Denoising from Degraded Rough Casual Photographs using Hopfield Neural Network," International Information Institute (Tokyo). Information, 2017; Vol. 20 No.4A 2513-2518, April 2017.