Presentation 1997/7/25
An On-line Handwritten Character Recognition Method based on Hidden Markov Models
Hitoshi ITOH, Masaki NAKAGAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes an on-line handwritten character recognition method based on Hidden Markov Models. The method applies HMMs to the sequence of quantized feature vectors extracted from an input pattern. The well-known Baum-Welch algorithm has been adopted for training the models. Our large database of handwritten character patterns employed for training makes the system robust against different stroke orders and peculiar patterns. Combining HMM probabilities obtained from two or three different feature sequences reduces the recognition errors for similar patterns. The effectiveness of the proposed method is shown through experiments on 76,340 character patterns of the 46 Hiragana categories.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) on-line handwritten character recognition / Hidden Markov Model / vector quantization
Paper # MVE97-70
Date of Issue

Conference Information
Committee MVE
Conference Date 1997/7/25(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An On-line Handwritten Character Recognition Method based on Hidden Markov Models
Sub Title (in English)
Keyword(1) on-line handwritten character recognition
Keyword(2) Hidden Markov Model
Keyword(3) vector quantization
1st Author's Name Hitoshi ITOH
1st Author's Affiliation Department of Computer Science Tokyo University of Agriculture and Technology()
2nd Author's Name Masaki NAKAGAWA
2nd Author's Affiliation Department of Computer Science Tokyo University of Agriculture and Technology
Date 1997/7/25
Paper # MVE97-70
Volume (vol) vol.97
Number (no) 207
Page pp.pp.-
#Pages 6
Date of Issue