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
Copyright Status
Unknown
Socpus ID
0029214129 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/0029214129
STARS Citation
Bebis, George; Georgiopoulos, Michael; and da Vitoria Lobo, Niels, "Learning Geometric Hashing Functions For Model-Based Object Recognition" (1995). Scopus Export 1990s. 1923.
https://stars.library.ucf.edu/scopus1990/1923