Robust 2-D Model-Based Object Recognition

Title: en_US Robust 2-D Model-Based Object Recognition
Creator: en_US Cass, Todd A.
Date: 2004-10-20T19:58:22Z
Date Available: 2004-10-20T19:58:22Z
Date Issued: en_US 1988-05-01
Identifier: en_US AITR-1132
uri: http://hdl.handle.net/1721.1/6823
Abstract: en_US Techniques, suitable for parallel implementation, for robust 2D model-based object recognition in the presence of sensor error are studied. Models and scene data are represented as local geometric features and robust hypothesis of feature matchings and transformations is considered. Bounds on the error in the image feature geometry are assumed constraining possible matchings and transformations. Transformation sampling is introduced as a simple, robust, polynomial-time, and highly parallel method of searching the space of transformations to hypothesize feature matchings. Key to the approach is that error in image feature measurement is explicitly accounted for. A Connection Machine implementation and experiments on real images are presented.
Extent: en_US 106 p.; 10585533 bytes; 7511134 bytes
Format: application/postscript; application/pdf
Language: en_US
Relation: en_US AITR-1132
Subject: en_US object recognition; en_US object localization; en_US parallel computation; en_US sensor uncertainty; en_US hough transform