The Community for Technology Leaders
Ninth International Workshop on Frontiers in Handwriting Recognition (2004)
Kokubunji, Tokyo, Japan
Oct. 26, 2004 to Oct. 29, 2004
ISSN: 1550-5235
ISBN: 0-7695-2187-8
pp: 232-237
Alessandro L. Koerich , Pontifical Catholic University of Paraná
Robert Sabourin , École de Technologie Supérieure
Ching Y. Suen , Concordia University
To support large vocabulary handwriting recognition in standard computer platforms, a fast algorithm for hidden Markov model alignment is necessary. To address this problem, we propose a non-heuristic fast decoding algorithm which is based on hidden Markov model representation of characters. The decoding algorithm breaks up the computation of word likelihoods into two levels: state level and character level. Given an observation sequence, the two level decoding enables the reuse of character likelihoods to decode all words in the lexicon, avoiding repeated computation of state sequences. In an 80,000-word recognition task, the proposed decoding algorithm is about 15 times faster than a conventional Viterbi algorithm, while maintaining the same recognition accuracy.
Alessandro L. Koerich, Robert Sabourin, Ching Y. Suen, "Fast Two-Level HMM Decoding Algorithm for Large Vocabulary Handwriting Recognition", Ninth International Workshop on Frontiers in Handwriting Recognition, vol. 00, no. , pp. 232-237, 2004, doi:10.1109/IWFHR.2004.42
184 ms
(Ver 3.3 (11022016))