A connected character recogniser using level building of HMMs

Proceedings - International Conference on Pattern Recognition

Volumn 2, Issue , 1994, Pages 439-441

  Elms, A J ^a  

^a UNIVERSITY OF SURREY   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

HIDDEN MARKOV MODELS; IMAGE SEGMENTATION; NEURAL NETWORKS; PHOTOCOPYING;

CONNECTED CHARACTERS; TEXT IMAGES; VERTICAL LINES;

CHARACTER RECOGNITION;

EID: 33747396379     PISSN: 10514651     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. M. Bokser, "Omnidocument Technologies," Proceedings of the IEEE, Vol. 80 (7), pp. 1066-1078, 1992.
2. L. Rabiner and S. Levinson, "A Speaker-Independent Syntax-Directed, Connected Word Recognition System Based on Hidden Markov Models and Level Building," IEEE Transactions on Acoustics, Speech and Signal Processing, Vol. 33 (3), pp. 561-573, 1985.
3. stInternationalConference on Document Analysis and Recognition, pp. 785-793, 1991.
4. C. Bose and S. Kuo, "Connected and Degraded Text Recognition Using Hidden Markov Model," in Proceedings of II International Conference on Pattern Recognition, pp. 116-119,1992.
5. J. Kittler and D. Pairman, "Optimaliry of reassignment rules in dynamic clustering," Pattern Recognition, Vol. 21 (2), pp. 169-174,1988.
6. H. Baird, "Document linage Defect Models," in Structured Document Image Analysis (H. Baird, H. Bunke, and K. Yamamoto, eds.), Springer-Verlag, 1992.