Use of discrete-state Markov process for Chinese-character recognition

Bor-Shenn Jeng; Chun-Hsi Shih; San-Wei Sun; Tieh-Min Wu; Bing-Shan Chien; Ming-Wen Chang

doi:10.1117/12.24181

1 September 1990 Use of discrete-state Markov process for Chinese-character recognition

Bor-Shenn Jeng, Chun-Hsi Shih, San-Wei Sun, Tieh-Min Wu, Bing-Shan Chien, Ming-Wen Chang

Proceedings Volume 1360, Visual Communications and Image Processing '90: Fifth in a Series; (1990) https://doi.org/10.1117/12.24181
Event: Visual Communications and Image Processing '90, 1990, Lausanne, Switzerland

Abstract

In this paper, an intelligent optical Chinese character recognition system using discrete-state Markov process has been developed to solve the input problem of Chinese characters. The doubly stochastic process encodes the distortion and similarity among patterns of a class through a stochastical and evaluating approach. A simple feature extraction is employed in our experiments, which is the histogram of the projected profiles. A character class is modeled by a 7-state Markov process, while the recognition rate for 5401 multi-font character classes reaches 97% on average for inside test and 92% on average for outside test.

Citation Download Citation

Bor-Shenn Jeng, Chun-Hsi Shih, San-Wei Sun, Tieh-Min Wu, Bing-Shan Chien, and Ming-Wen Chang "Use of discrete-state Markov process for Chinese-character recognition", Proc. SPIE 1360, Visual Communications and Image Processing '90: Fifth in a Series, (1 September 1990); https://doi.org/10.1117/12.24181

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available