Share Email Print

Proceedings Paper

Handwritten digits recognition using HMM and PSO based on storks
Author(s): Liao Yan; Zhenhong Jia; Jie Yang; Shaoning Pang
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A new method for handwritten digits recognition based on hidden markov model (HMM) and particle swarm optimization (PSO) is proposed. This method defined 24 strokes with the sense of directional, to make up for the shortage that is sensitive in choice of stating point in traditional methods, but also reduce the ambiguity caused by shakes. Make use of excellent global convergence of PSO; improving the probability of finding the optimum and avoiding local infinitesimal obviously. Experimental results demonstrate that compared with the traditional methods, the proposed method can make most of the recognition rate of handwritten digits improved.

Paper Details

Date Published: 21 July 2010
PDF: 5 pages
Proc. SPIE 7749, 2010 International Conference on Display and Photonics, 774914 (21 July 2010); doi: 10.1117/12.869532
Show Author Affiliations
Liao Yan, Xinjiang Univ. (China)
Zhenhong Jia, Xinjiang Univ. (China)
Jie Yang, Shanghai Jiaotong Univ. (China)
Shaoning Pang, Auckland Univ. of Technology (Australia)

Published in SPIE Proceedings Vol. 7749:
2010 International Conference on Display and Photonics

© SPIE. Terms of Use
Back to Top