Share Email Print

Proceedings Paper

Unsupervised Feature Selection For Object Recognition
Author(s): Jakub Segen
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 method for selecting features for object recognition based on training data is proposed. This method avoids overspecifying or selecting too many features by using the criterion of minimal representation, which penalizes the representation complexity of features. The presented approach can be used to search for high level structural features such as relations or production rules.

Paper Details

Date Published: 23 May 1983
PDF: 4 pages
Proc. SPIE 0360, Robotics and Industrial Inspection, (23 May 1983); doi: 10.1117/12.934094
Show Author Affiliations
Jakub Segen, Bell Laboratories (United States)

Published in SPIE Proceedings Vol. 0360:
Robotics and Industrial Inspection
David P. Casasent, Editor(s)

© SPIE. Terms of Use
Back to Top