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

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

DOI QR Code

A study on the Fuzzy Recurrent Neural Networks for the image noise elimination filter

영상 잡음 제거 필터를 위한 퍼지 순환 신경망 연구

  • 변오성 (현대모비스 기술연구소)
  • Received : 2011.03.28
  • Accepted : 2011.05.16
  • Published : 2011.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, it is realized an image filter for a noise elimination using a recurrent neural networks with fuzzy. The proposed fuzzy neural networks structure is to converge weights and the number of iteration for a certain value by using basically recurrent neural networks structure and is simplified computation and complexity of mathematics by applying the hybrid fuzzy membership function operator. In this paper, the proposed method, the recurrent neural networks applying fuzzy which is collected a certain value, has been proved improving average 0.38dB than the conventional method, the generalied recurrent neural networks, by using PSNR. Also, a result image of the proposed method was similar to the original image than a result image of the conventional method by comparing to visual images.

본 논문은 퍼지를 적용한 순환 신경망을 이용하여 잡음 제거용 필터를 구현하였다. 제안된 퍼지 순환 신경망 구조는 기본적으로 순환 신경망 구조를 이용하여 가중치 및 반복횟수가 일정한 값에 수렴하도록 하였으며, 하이브리드 퍼지 소속 함수 연산자를 적용하여 수학적인 계산량 및 복잡성를 단순화하였다. 본 논문은 제안된 퍼지 순환 신경망 구조 필터가 일반적인 순환 신경망 구조 필터보다 평균 0.38dB 정도 영상복원이 개선됨을 PSNR을 이용하여 증명하였다. 또한 결과 영상 비교에서 제안된 방법을 적용하여 얻은 영상이 기존 방법을 적용하여 얻은 영상보다 원영상과 더 유사함을 확인하였다.

Keywords

References

  1. D. K. Lee, M. J. Park, J. W. Kim, D. Y. Kim. D. W. Kim and D. H. Lim, "Support Vector Machine and Improved Adaptive Median Filtering for Impulse Noise Removal from Images," Journal of KSS, Vol. 23(1), pp. 151-165, 2010.
  2. J. R. Mohammed, "An improved median filter based on efficient noise detection for high quality image restoration," AICMS, Modeling & Simulation, pp 217-331, 2008.
  3. T. W. Baek and S. I. Lee, "An Iterative Bilateral Weighted Median Filter for the Removal of High-Density Impulse Noise," KIIT Review, Vol. 8, No. 2, pp. 59-65, Feb. 2010.
  4. P. Ng and K. Ma, "Switching Median Filter with Boundary Discriminative noise detection," IEEE Trans., Image Process. Vol. 15, No. 6, pp. 1506-1516, Jun. 2006. https://doi.org/10.1109/TIP.2005.871129
  5. R. K. Kulkarni, C. B. Lahoti and S. Meher, "Impulse denoising using improved progressive switching median filter," Proceedings of the International Conference and Workshop on Emerging Trends in Technology, Feb. 2010.
  6. T. Chen and Hong Ren Wu, "Adaptive Impulse Detection using Center-Weighted Median Filters," IEEE Trans. Signal Processing Letters, vol. 8, pp. 1-3, 2001. https://doi.org/10.1109/97.889633
  7. T. C. Lin and P. Y. Yu, "Adaptive two-pass median filter based on support vector machines for image restroation," Neural Computation, Vol. 16, pp. 333-354, 2004 https://doi.org/10.1162/neco.2004.16.2.333
  8. Ezequiel Lopez-Rubio, "Restoration of images corrupted by Gaussian and uniform impulsive noise," Pattern Recognition, Vol. 43 No. 5, pp.1835-1846, May, 2010
  9. H. Kong and L. Guan, "A Neural Network Adaptive Filter for the Removal of Impulse Noise in Digital Images," Neural Networks, Vol. 9, pp. 373-378, Apr. 1996. https://doi.org/10.1016/0893-6080(95)00128-X
  10. C. C. Ku and K. Y. Lee, "Diagonal Recurrent neural networks for dynamic system control," IEEE Trans. on Neural Networks, Vol. 6, No. 1, pp. 144-156, 1995. https://doi.org/10.1109/72.363441
  11. S. Ong, C. You, S. Choi and D. Hong, "A decision feedback Recurrent neural equalizer as an infinite impulse response filter," IEEE Trans. on Signal Processing, Vol. 45, No. 11, pp. 2851-2858, 1997. https://doi.org/10.1109/78.650112
  12. J. A. Nossek, G. Seiler, T. Roska and L. O. Chua, "Cellular neural networks: theory and circuit design," Int j. circuits. theory. no. 20, pp. 523-543, Apr. 1992.
  13. S. Y. Kung, "Digital Neural Networks" Prentice Hall, International, Inc., pp. 203-236, 1993.
  14. T. Yang and L. B. Yang, "The global stability of fuzzy cellular neural network," IEEE Trans. circuit system. I, Vol. 43, pp, 880-883, Oct. 1996. https://doi.org/10.1109/81.538999
  15. Abraham Kandel, Gideon Langholz, "Fuzzy Hardware," Kluwer Academic Publishers, 1998.
  16. O. S. Byun, "An efficient Color Edge Fuzzy interpolation Method for improving a Chromatic Aberration," Journal of KSCI, Vol. 15, No. 10, pp. 59-70, Oct. 2010.
  17. H. J. Jung and C. Y. Jung, "Development of Information Systems Model Applying Fuzzyset Theory," Journal of KSCI, Vol. 9, No. 4, pp. 203-214, Dec. 2004.

Cited by

  1. Noise Reduction by Filter Improvement in Mixed Noise Image vol.50, pp.5, 2013, https://doi.org/10.5573/ieek.2013.50.5.231