Share Email Print

Proceedings Paper

New construction method of bidirectional associative memory for object recognition
Author(s): Te-Shin Chen; Kang-Ping Lin; Being-Tau Chung
Format Member Price Non-Member Price
PDF $14.40 $18.00
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 construction method of bi-directional associative memory (BAM) for image pattern/object recognition is proposed in this paper. The strategy of the method is based on combining the major information of each object from both spatial domain and frequency domain images. The BAM model is reconstructed by input object features and the input object's Fourier spectrum. After the BAM reconstruction, each similar input pattern can be retrieved or recognized using the two-layer neural network automatically. The presented reconstruction method allows any new input object to be stored and added into the original BAM model without extra training procedure. Experimental results indicate that the system performs good recognition ability for input object with noise. The method also provides a distortion correction way for the deformed objects. The system has been implemented in a PC- based computer.

Paper Details

Date Published: 27 February 1996
PDF: 7 pages
Proc. SPIE 2727, Visual Communications and Image Processing '96, (27 February 1996); doi: 10.1117/12.233229
Show Author Affiliations
Te-Shin Chen, Chung-Yuan Univ. (Taiwan)
Kang-Ping Lin, Chung-Yuan Univ. (Taiwan)
Being-Tau Chung, Chung-Yuan Univ. (Taiwan)

Published in SPIE Proceedings Vol. 2727:
Visual Communications and Image Processing '96
Rashid Ansari; Mark J. T. Smith, Editor(s)

© SPIE. Terms of Use
Back to Top