Share Email Print

Proceedings Paper

Biologically inspired feature-based categorization of objects
Author(s): T. Nathan Mundhenk; Vidhya Navalpakkam; Hendrik Makaliwe; Shrihari Vasudevan; Laurent Itti
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

We have developed a method for clustering features into objects by taking those features which include intensity, orientations and colors from the most salient points in an image as determined by our biologically motivated saliency program. We can train a program to cluster these features by only supplying as training input the number of objects that should appear in an image. We do this by clustering from a technique that involves linking nodes in a minimum spanning tree by not only distance, but by a density metric as well. We can then form classes over objects or object segmentation in a novel validation set by training over a set of seven soft and hard parameters. We discus as well the uses of such a flexible method in landmark based navigation since a robot using such a method may have a better ability to generalize over the features and objects.

Paper Details

Date Published: 7 June 2004
PDF: 12 pages
Proc. SPIE 5292, Human Vision and Electronic Imaging IX, (7 June 2004); doi: 10.1117/12.527321
Show Author Affiliations
T. Nathan Mundhenk, Univ. of Southern California (United States)
Aerospace Corp. (United States)
Vidhya Navalpakkam, Univ. of Southern California (United States)
Hendrik Makaliwe, Univ. of Southern California (United States)
Shrihari Vasudevan, Univ. of Southern California (United States)
Laurent Itti, Univ. of Southern California (United States)

Published in SPIE Proceedings Vol. 5292:
Human Vision and Electronic Imaging IX
Bernice E. Rogowitz; Thrasyvoulos N. Pappas, Editor(s)

© SPIE. Terms of Use
Back to Top