The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지

A Study on Enhanced Self-Generation Supervised Learning Algorithm for Image Recognition

영상 인식을 위한 개선된 자가 생성 지도 학습 알고리듬에 관한 연구

  • 김태경 (중앙대학교 첨단영상대학원 영상공학과 시각및지능시스템연구실) ;
  • 김광백 (신라대학교 공과대학 컴퓨터공학과) ;
  • 백준기 (중앙대학교 첨단영상대학원 영상공학과 시각및지능시스템연구실)
  • Published : 2005.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

we propose an enhanced self-generation supervised algorithm that by combining an ART algorithm and the delta-bar-delta method. Form the input layer to the hidden layer, ART-1 and ART-2 are used to produce nodes, respectively. A winner-take-all method is adopted to the connection weight adaption so that a stored pattern for some pattern is updated. we test the recognition of student identification, a certificate of residence, and an identifier from container that require nodes of hidden layers in neural network. In simulation results, the proposed self-generation supervised learning algorithm reduces the possibility of local minima and improves learning speed and paralysis than conventional neural networks.

오류 역전파 알고리즘의 문제점과 ART 신경회로망의 문제점을 개선하기 위해 Jacobs가 제안한 delta-bar-delta 방법과 신경회로망을 결합한 자가 생성 지도 학습 알고리듬을 제안한다. 입력층과 은닉층에서는 ART-1과 ART-2 알고리듬을 이용하고, winner-take-all 방식은 완전 연결 구조이나 연결된 가중치만을 조정하도록 채택하였다. 실험을 위해 학생증, 주민등록증, 컨테이너의 영상으로 추출한 패턴을 신경회로망의 은닉층 노드에 대해 실험하였고, 실험결과 제안된 자기 생성 지도 학습알고리듬이 지역최소화, 학습 속도, 정체 현상이 기존의 방법보다 성능이 개선된 것을 확인하였다.

Keywords

References

  1. Rumelhart, D. E., Hintion, G. E., & Williams, R. J., 'Learning representation by back propagation errors.' Nature, 323, 533-536, 1986 https://doi.org/10.1038/323533a0
  2. R. C. Gonzalez and R. E. Woods, Digital Image Processing, Addison Wedley, 1992
  3. Rumelhart, D. E. McClelland, J. L. and the PDP Reserch Group(Eds), parallel distributed processing, vol. 1, pp. 318-536, Cambridge, MA: MIT Press
  4. James A. Freeman, David M. Skapura, Neural Networks Algorithms, applications, and Programming Techiques, addison Wesley, pp. 89-125, 1991
  5. M. Georipoulos, G. L. Heileman and J. Huang, 'Properties of Learning Related to Pattern Diversity in ARTl,' Neural Networks, vol. 1, pp. 751-757, 1991
  6. K. B. Kim and K. C. Kim, 'A Study on Face Recognition using New Fuzzy ART,' Proceedings of ITC-CSCC, vol. 2, pp. 1057-1060, 1998
  7. Gail A. Carpenter and Stephen Grossberg, 'The ART of Adaptive Pattern Recognition by a Self-Organizing Neural Networks,' IEEE Computers, pp. 77-88, 1988
  8. Gail A. Carpenter and Stephen Grossberg, 'A Massively Parallel Architecture for a Self-organizing Neural Pattern Recognition Machine,' Computer Vision, Graphics, and Image Processing, vol. 37, pp. 54-115, 1987 https://doi.org/10.1016/S0734-189X(87)80014-2
  9. R. Allen, 'Several Studies on Natural Language and Back Propagation,' IEEE ICNN, vol. II, pp. 335-342, 1987
  10. R. A. Jacobs, 'Increased rates of convergence through learning rate adaptation,' Neural Networks, vol. 1, no. 4, pp. 295-308, 1988
  11. J. W. Kim, et, al., 'Auto-Tuning Method of Learning Rate for Performance Improvement of Back propagation Algorithm,' The Institute of Electronics Engineers of Korea, vol. 39, no. 4, pp. 19-26, 2002
  12. T. K. Kim, et, al., 'An Educational Matters Administration System on The web by Using Image Recognition,' Korea Intelligent Information Systems Society, pp. 203-209, 2002
  13. J. U. Ryu, T. K. Kim, K. B. Kim, 'An Enhanced Fuzzy ART Algorithm for The Identifier Recognition form Shiping Container image,' Korea Fuzzy Logic and Intelligent Systems Society, vol. 12, no. 2, pp. 365-369, 2002
  14. Y. H. Ju, T. K. Kim, K. B. Kim, 'A Study on Auto-Tuning Method of Learning Rate by Using Fuzzy Logic System,' Korea Fuzzy Logic and Intelligent Systems Society, pp. 484-489, 2003