인과 2D 은닉 마르코프 모델

Causal 2D Hidden Markov Model

  • 신봉기 (부경대학교 전자컴퓨터정보통신공학부)
  • Sin, Bong-Gi (Dept.of Electronics Computer Information Communication Engineering, Pukyong National University)
  • 발행 : 2001.01.01

초록

2D로 확장한 HMM은 다수 제안되었지만 엄밀한 의미에 있어서 2D HMM이라고 하기에 부족한 점이 많다. 본 논문에서는 기존의 랜덤 필드 모형이 아닌 새로운 2D HMM을 제안한다. 상하 및 좌우 방향의 causal chain 관계를 가정하고 완전한 격자 형성 조건을 두어 2D HMM의 평가, 매개 변수를 추정하는 알고리즘을 제시하였다. 각각의 알고리즘은 동적 프로그래밍과 최우 추정법에 근거한 것이다. 변수 추정 알고리즘은 반복적으로 이루어지며 국소 최적치에 수렴함을 보였다.

키워드

참고문헌

  1. O. Agazzi and S. Kuo, 'Pseudo two-dimensional hidden Markov models for document recognition,' AT&T Technical Journal, vol. 72, no. 5, Sep. 1993
  2. G. Saon, 'Cursive word recognition using a random field based hidden Markov model,' Int'l J. Doc. Aanal. and Recog., vol. 1, no. 4, pp. 199-208, 1999 https://doi.org/10.1007/s100320050019
  3. W. Cho, S. Lee and J. Kim, 'Modeling and recognition of cursive words with hidden Markov models,' Pattern recognition, vol. 28, no. 12, pp. 1941-1953, 1995 https://doi.org/10.1016/0031-3203(95)00041-0
  4. B.-K. Sin and J. H. Kim, 'Ligature modeling for online cursive script recognition,' IEEE Trans PAMI, vol. 19, no. 6, June 1997 https://doi.org/10.1109/34.601250
  5. S. Geman and D. Geman, 'Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images,' IEEE Trans. PAMI, vol. PAMI-6, no. 6, Nov. 1984
  6. C. Acuna, 'Texture modeling using Gibbs distributions,' CVGIP: Graphical Models and Image Processing, vol. 54, no. 3, pp. 210-222, May 1992 https://doi.org/10.1016/1049-9652(92)90052-Y
  7. D. Pickard, 'A Curious Binary Lattice Process,' J. Applied Probability, vol. 14, pp. 717-731, 1977 https://doi.org/10.2307/3213345
  8. J. Woods, 'Two-Dimensional Discrete Markovian Fields,' IEEE Trans. Info. Theoiy, vol. IT-18, no. 2, March 1972
  9. A. Jain, 'Advances in Mathematical Models for Image processing,' Proc. IEEE, vol. 69, pp. 502-528, 1981
  10. F. Spitzer, 'Markov random field and Gibbs ensembles,' Amer. Math. Mon., vol. 78, pp. 142-154, 1971
  11. L. Kanal, 'Markov Mesh Models,' Computer Graphics and Image Processing, vol. 12, pp. 371-375, 1980
  12. S. Lakshmanan and H. Derin, 'Simultaneous Parameter Estimation and Segmentation of Gibbs Random Fields Using Simulated Annealing,' IEEE Trans. PAMI, vol. 11, no. 8, Aug. 1980 https://doi.org/10.1109/34.31443
  13. Y. Zhao, X. Zhuang, L. Atlas and L. Anderson, 'Parameter Estimation and Restoration of Noisy Images Using Gibbs Distributions in Hidden Markov Models,' CVGIP: Graphical Models and Image Processing, vol. 54, no. 3, pp. 187-197, May 1992 https://doi.org/10.1016/1049-9652(92)90050-8
  14. J. Zhang, 'The Mean Field Theory in EM Procedures for Blind Markov Random Field Image Restoration,' IEEE Traits. Image Processing, vol. 2, no. 1, pp. 27-40, Jan. 1993 https://doi.org/10.1109/83.210863
  15. L. B'aum and J. Eagon, 'An inequality with applications to statistical estimation' for probabilistic functions of a Markov process and to a models for ecology,' Bull. Ann. Math Stat., vol. 73, pp. 360-363, 1967