Share Email Print
cover

Proceedings Paper

Hybrid pyramid/neural network object recognition
Author(s): P. Anandan; Peter J. Burt; John C. Pearson; Clay D. Spence
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This work concerns computationally efficient computer vision methods for the search for and identification of small objects in large images. The approach combines neural network pattern recognition with pyramid-based coarse-to-fine search, in a way that eliminates the drawbacks of each method when used by itself and, in addition, improves object identification through learning and exploiting the low-resolution image context associated with the objects. The presentation will describe the system architecture and the performance on illustrative problems.

Paper Details

Date Published: 25 February 1994
PDF: 6 pages
Proc. SPIE 2103, 22nd AIPR Workshop: Interdisciplinary Computer Vision: Applications and Changing Needs, (25 February 1994); doi: 10.1117/12.169460
Show Author Affiliations
P. Anandan, David Sarnoff Research Ctr. (United States)
Peter J. Burt, David Sarnoff Research Ctr. (United States)
John C. Pearson, David Sarnoff Research Ctr. (United States)
Clay D. Spence, David Sarnoff Research Ctr. (United States)


Published in SPIE Proceedings Vol. 2103:
22nd AIPR Workshop: Interdisciplinary Computer Vision: Applications and Changing Needs
J. Michael Selander, Editor(s)

© SPIE. Terms of Use
Back to Top