Conference proceeding
Selecting canonical views for view-based 3-D object recognition
Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004, v 2, pp 273-276
2004
Abstract
Given a collection of sets of 2-D views of 3-D objects and a similarity measure between them, we present a method for summarizing the sets using a small subset called a bounded canonical set (BCS), whose members best represent the members of the original set. This means that members of the BCS are as dissimilar from each other as possible, while at the same time being as similar as possible to the nonBCS members. This paper would extend our earlier work on computing canonical sets [Denton, T, et al., June 2004] in several ways: by omitting the need for a multi-objective optimization, by allowing the imposition of cardinality constraints, and by introducing a total similarity function. We evaluate the applicability of BCS to view selection in a view-based object recognition environment.
Metrics
Details
- Title
- Selecting canonical views for view-based 3-D object recognition
- Creators
- T Denton - Drexel Univ., Philadelphia, PA, USAM.F Demirci - Drexel Univ., Philadelphia, PA, USAJ Abrahamson - Drexel Univ., Philadelphia, PA, USAA Shokoufandeh - Drexel UniversityS Dickinson
- Publication Details
- Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004, v 2, pp 273-276
- Publisher
- IEEE
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science
- Web of Science ID
- WOS:000223877400066
- Scopus ID
- 2-s2.0-10044289318
- Other Identifier
- 991019168841704721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Computer Science, Artificial Intelligence