Landmark-based partial shape recognition by a BAM neural network

Document Type

Conference Proceeding

Publication Date

1-1-1991

Abstract

In this paper, we develop a bidirectional associative memory (BAM) based neural network to achieve high-speed partial shape recognition. To recognize objects which are partially occluded, we represent each object by a set of landmarks. The landmarks of an object are points of interest relative to the object that have important shape attributes. To achieve recognition, feature values (landmark values) of each model object are trained and stored in the network. Each memory cell is trained to store landmark values of a model object for all possible positions. Given a scene which may consist of several objects, landmarks in the scene are first extracted, and their corresponding landmark values are computed. Scene landmarks values are entered to each trained memory cell. The memory cell is shown to be able to recall the position of the model object in the scene. A heuristic measure is then computed to validate the recognition.

Identifier

0026382470 (Scopus)

ISBN

[0819407437, 9780819407436]

Publication Title

Proceedings of SPIE the International Society for Optical Engineering

External Full Text Location

https://doi.org/10.1117/12.50317

ISSN

0277786X

First Page

1069

Last Page

1079

Issue

pt 2

Volume

1606

This document is currently not available here.

Share

COinS