A Bayesian model for efficient visual search and recognition

Lior Elazary; Laurent Itti

doi:10.1016/j.visres.2010.01.002

A Bayesian model for efficient visual search and recognition

Vision Res. 2010 Jun 25;50(14):1338-52. doi: 10.1016/j.visres.2010.01.002. Epub 2010 Jan 18.

Authors

Lior Elazary¹, Laurent Itti

Affiliation

¹ Department of Computer Science, University of Southern California, Los Angeles, CA 90089-2520, USA. elazary@usc.edu

PMID: 20080120
DOI: 10.1016/j.visres.2010.01.002

Abstract

Humans employ interacting bottom-up and top-down processes to significantly speed up search and recognition of particular targets. We describe a new model of attention guidance for efficient and scalable first-stage search and recognition with many objects (117,174 images of 1147 objects were tested, and 40 satellite images). Performance for recognition is on par or better than SIFT and HMAX, while being, respectively, 1500 and 279 times faster. The model is also used for top-down guided search, finding a desired object in a 5x5 search array within four attempts, and improving performance for finding houses in satellite images.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Attention / physiology
Bayes Theorem*
Humans
Models, Biological*
Recognition, Psychology
Signal Detection, Psychological / physiology
Visual Perception / physiology*