Share Email Print

Proceedings Paper

Generalized bidirectional associative memories for image processing
Author(s): Arun D. Kulkarni; Iraj Yazdapanhi
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The bidirectional associative memory (BAM) so far is limited to two input/output patterns. Recently, Humpert has suggested the generalization of the BAM to a bidirectional associative memory with several input/output patterns (BAMg). The generalization of the BAM to the BAMg raises several interesting questions regarding the inter-connections and updating of neuron fields. Some of the possible configurations of the BAMg are investigated in the paper. The BAMg is very useful in many image processing applications where-in storage and retrieval of sets of images is required. Each set may contain two or more images. In this paper, we have developed a software simulation for the BAMg, and have used the BAMg to store and retrieve three sets of images. Each set consists of three images. During the retrieval partial or noisy images are used as the stimulus vectors to retrieve corresponding images in other sets. The results are presented in the paper.

Paper Details

Date Published: 1 November 1992
PDF: 8 pages
Proc. SPIE 1826, Intelligent Robots and Computer Vision XI: Biological, Neural Net, and 3D Methods, (1 November 1992); doi: 10.1117/12.131595
Show Author Affiliations
Arun D. Kulkarni, Univ. of Texas/Tyler (United States)
Iraj Yazdapanhi, Univ. of Texas/Tyler (United States)

Published in SPIE Proceedings Vol. 1826:
Intelligent Robots and Computer Vision XI: Biological, Neural Net, and 3D Methods
David P. Casasent, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?