Geometric Aspects of Visual Object Recognition

Title: en_US Geometric Aspects of Visual Object Recognition
Creator: en_US Breuel, Thomas M.
Date: 2004-11-19T17:19:47Z
Date Available: 2004-11-19T17:19:47Z
Date Issued: en_US 1992-05-01
Identifier: en_US AITR-1374
uri: http://hdl.handle.net/1721.1/7342
Abstract: en_US This thesis presents there important results in visual object recognition based on shape. (1) A new algorithm (RAST; Recognition by Adaptive Sudivisions of Tranformation space) is presented that has lower average-case complexity than any known recognition algorithm. (2) It is shown, both theoretically and empirically, that representing 3D objects as collections of 2D views (the "View-Based Approximation") is feasible and affects the reliability of 3D recognition systems no more than other commonly made approximations. (3) The problem of recognition in cluttered scenes is considered from a Bayesian perspective; the commonly-used "bounded-error errorsmeasure" is demonstrated to correspond to an independence assumption. It is shown that by modeling the statistical properties of real-scenes better, objects can be recognized more reliably.
Extent: en_US 173 p.; 33022903 bytes; 26499530 bytes
Format: application/postscript; application/pdf
Language: en_US
Relation: en_US AITR-1374
Subject: en_US computer vision; en_US bouded error; en_US point matching; en_US 3D objectsrecognition