Title :
An a priori indicator of the discrimination power of discrete hidden Markov models
Author :
Grandidier, F. ; Sabourin, R. ; Gilloux, M. ; Suen, CY
Author_Institution :
CENPARMI, Concordia Univ., Montreal, Que., Canada
fDate :
6/23/1905 12:00:00 AM
Abstract :
During the development of a hidden Markov model based handwriting recognition system, the testing phase takes a non-negligible amount of computation time. This is especially true for real application where the lexicon size is large. In order to shorten the development process, we propose an indicator of the system discrimination power. This indicator is calculated during training and its final value is obtained at the end of the training phase, without more calculation. Its definition consists of a modification of the observation probability of the validation corpus by the trained system. Some experiments were carried out and the results show clearly the correlation between this indicator and recognition rates
Keywords :
handwriting recognition; hidden Markov models; image recognition; probability; a priori indicator; development process; discrete hidden Markov models; discrimination power; handwriting recognition system; lexicon size; non-negligible time; observation probability; real application; recognition rates; system discrimination power; testing phase; trained system; training phase; validation corpus; Computer architecture; Data mining; Handwriting recognition; Hidden Markov models; Iterative algorithms; Performance evaluation; Power system modeling; Speech recognition; System testing; Vocabulary;
Conference_Titel :
Document Analysis and Recognition, 2001. Proceedings. Sixth International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7695-1263-1
DOI :
10.1109/ICDAR.2001.953812