Title

Learning Geometric Hashing Functions For Model-Based Object Recognition

Abstract

A new approach is proposed for alleviating the problem of non-uniform distribution of invariants over the hash space. This approach is based on the use of an 'elastic hash tube' which is implemented as a Self-Organizing Feature Map Neural Network (SOFM-NN). The advantages of the proposed approach is that it is a process that adapts to the invariants through learning. Hence, it makes absolutely no assumptions about the statistical characteristics of the invariants and geometric hash function is actually computed through learning. Moreover, the well-known 'topology preserving' property of the SOFM-NN guarantees that the computed geometric hash function should be well behaved.

Publication Date

1-1-1995

Publication Title

IEEE International Conference on Computer Vision

Number of Pages

543-548

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

Socpus ID

0029214129 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/0029214129

This document is currently not available here.

Share

COinS