Discriminative training for HMM-Based offline handwritten character recognition

Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

Volumn 2003-January, Issue , 2003, Pages 114-118

  Nopsuwanchai, Roongroj ^a   Povey, Dan ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

PRINCIPAL COMPONENT ANALYSIS; STEREOPHONIC BROADCASTING;

COMPOSITE IMAGES; DISCRIMINATIVE TRAINING; HAND WRITTEN CHARACTER RECOGNITION; HANDWRITING RECOGNITION; IMPROVE PERFORMANCE; MAXIMUM MUTUAL INFORMATION; OFF-LINE HANDWRITTEN; TRAINING DATABASE;

CHARACTER RECOGNITION;

EID: 33845866717     PISSN: 15205363     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICDAR.2003.1227643     Document Type: Conference Paper

References (5)

1. A. Biem. Minimum classification error training of hidden markov model for handwriting recognition. In Proc. ICASSP'01, volume 3, pages 1529-1532, 2001.
2. M. Tistarelli and G. Sandini. On the advantage of polar and log-polar mapping for direct estimation of time-to-impact from optical flow. IEEE Trans. on Pattern Analysis and Machine Intelligence, 15(4):401-410, 1993.
3. A. Vinciarelli and S. Bengio. Offline cursive word recognition using continuous density hmms trained with pca or ica features. In Proc. ICPR'02, volume 3, pages 81-84, 2002.
4. P. Woodland and D. Povey. Large scale discriminative training for speech recognition. In Proc. ISCA ITRW ASR2000, pages 7-16, 2002.
5. P. Woodland and D. Povey. Large scale discriminative training of hidden markov models for speech recognition. Computer Speech and Language, 16(1):401-410, 2002.