The University of Edinburgh -
Division of Informatics
Forrest Hill & 80 South Bridge

Research Paper #717

Title:Best-First and Ten Other Variations of the Interpretation-Tree Model Matching Algorithm
Date:Sep 1994
Presented:Submitted to the AI Jounal
Keywords:model-based vision, model matching, object recognition
Abstract:The best known control algorithm for symbolic model matching in computer vision is the Interpretation Tree search algorithm, popularized and extended by Grimson, Lozano-Perez, Huttenlocher and others. This algorithm has a high computational complexity when applied to matching problems with large numbers of features. This paper examines eleven variations of this algorithm in a search for improved performance, and concludes that a best-first algorithm has greatly reduced theoretical complexity and runs much faster than the standard algorithm.

[Search These Pages] [DAI Home Page] [Comment]