Subset selection for active object recognition

Jay Winkeler, B.S. Manjunath, and S. Chandrasekaran
Department of Electrical and Computer Engineering
University of California, Santa Barbara, CA 93106-9560
jay [at], manj [at], shiv [at]


This paper presents an algorithm for constructing object representations suitable for recognition. The system automatically selects a representative subset of the views of the object while constructing the eigenspace basis. These views are actively located for object identification and pose determination. All processing is performed on-line. The camera is actively positioned during both representation and recognition. When tested with 240 views for each of seven objects, the system achieves 100% accurate object recognition and pose determination. These results are shown to degrade gracefully as conditions deteriorate.
[PDF] [BibTex]
J. Winkeler, B. S. Manjunath and S.Chandrasekaran,
IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 511-516, Fort Collins, CO, USA, Jun. 1999.
Node ID: 296 , DB ID: 93 , VRLID: 69 , Lab: VRL , Target: Proceedings
Subject: [Object-Based Retrieval] « Look up more