Recognition of handwritten word: first and second order hidden Markov model based approach

Author

Kundu, Amlan ; He, Yang ; Bahl, Paramvir

Author_Institution

Dept. of Electr. Eng., State Univ., of New York, Buffalo, NY, USA

fYear

1988

fDate

5-9 Jun 1988

Firstpage

457

Lastpage

462

Abstract

The handwritten word recognition problem is modeled in the framework of the hidden Markov model (HMM). The states of HMM are identified with the letters of the alphabet. The optimum symbols are then generated experimentally using 15 different features. Both the first- and second-order HMMs are proposed for the recognition tasks. Using the existing statistical knowledge of English, the calculation scheme of the model parameters are immensely simplified. Once the model is established, the Viterbi algorithm is used to recognize the sequence of letters consisting the word. Some experimental results are also provided indicating the success of the scheme

Keywords

Markov processes; character recognition; English; Markov processes; Viterbi algorithm; character recognition; handwritten word recognition; hidden Markov model based approach; statistical knowledge; Handwriting recognition; Hidden Markov models; Natural languages; Probability distribution; Speech processing; Speech recognition; Stochastic processes; Tin; Vocabulary; Writing;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision and Pattern Recognition, 1988. Proceedings CVPR '88., Computer Society Conference on

Conference_Location

Ann Arbor, MI

ISSN

1063-6919

Print_ISBN

0-8186-0862-5

Type

conf

DOI

10.1109/CVPR.1988.196275

Filename

196275