Selecting Canonical Views for View-Based 3-D Object Recognition

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 will extend our earlier work on computing canonical sets [2] 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.

• Type: Conference
• Year: 2004
• Where: ICPR
• Authors: Ali Shokoufandeh, Jeff Abrahamson, M. Fatih Demirci, Sven J. Dickinson, Trip Denton
• Keywords: Canonical Sets, Computer Vision, ICPR 2004, Total Similarity Function, View-based Object Recognition