Character recognition by synergetic neural network based on selective attention parameters

Mingxiang Wang; Yulong Mo; Junli Ma

doi:10.1117/12.477402

25 March 2003 Character recognition by synergetic neural network based on selective attention parameters

Mingxiang Wang, Yulong Mo, Junli Ma

Proceedings Volume 5015, Applications of Artificial Neural Networks in Image Processing VIII; (2003) https://doi.org/10.1117/12.477402
Event: Electronic Imaging 2003, 2003, Santa Clara, CA, United States

Abstract

In this paper a learning algorithm of synergetic neural network based on selective attention parameters is proposed. According to the mechanism of the Human Visual System (HVS), the weight matrix of synergetic neural network can be obtained by multiplying the prototype matrix by selective attention parameters. Two selective attention models based on the human visual system are put forward in this paper. The comparative experiments between the traditional algorithm SCAP and the new method we proposed in the application of recognizing the real gray images of numeric and alphabetic characters are done. And the results show that our method can improve the synergetic neural network's recognition performance and be more suitable to human visual system.

Citation Download Citation

Mingxiang Wang, Yulong Mo, and Junli Ma "Character recognition by synergetic neural network based on selective attention parameters", Proc. SPIE 5015, Applications of Artificial Neural Networks in Image Processing VIII, (25 March 2003); https://doi.org/10.1117/12.477402

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