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.
Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/7342 |
Date | 01 May 1992 |
Creators | Breuel, Thomas M. |
Source Sets | M.I.T. Theses and Dissertation |
Language | en_US |
Detected Language | English |
Format | 173 p., 33022903 bytes, 26499530 bytes, application/postscript, application/pdf |
Relation | AITR-1374 |
Page generated in 0.0016 seconds