Hierarchical Object Recognition Using Libraries of Parameterized Model Sub-Parts

Item

Title
en_US Hierarchical Object Recognition Using Libraries of Parameterized Model Sub-Parts
Creator
en_US Ettinger, Gil J.
Date
2004-10-20T20:10:29Z
Date Available
2004-10-20T20:10:29Z
Date Issued
en_US 1987-05-01
Identifier
en_US AITR-963
uri
http://hdl.handle.net/1721.1/6955
Abstract
en_US This thesis describes the development of a model-based vision system that exploits hierarchies of both object structure and object scale. The focus of the research is to use these hierarchies to achieve robust recognition based on effective organization and indexing schemes for model libraries. The goal of the system is to recognize parameterized instances of non-rigid model objects contained in a large knowledge base despite the presence of noise and occlusion. Robustness is achieved by developing a system that can recognize viewed objects that are scaled or mirror-image instances of the known models or that contain components sub-parts with different relative scaling, rotation, or translation than in models. The approach taken in this thesis is to develop an object shape representation that incorporates a component sub-part hierarchy- to allow for efficient and correct indexing into an automatically generated model library as well as for relative parameterization among sub-parts, and a scale hierarchy- to allow for a general to specific recognition procedure. After analysis of the issues and inherent tradeoffs in the recognition process, a system is implemented using a representation based on significant contour curvature changes and a recognition engine based on geometric constraints of feature properties. Examples of the system's performance are given, followed by an analysis of the results. In conclusion, the system's benefits and limitations are presented.
Extent
18376287 bytes
7041712 bytes
Format
application/postscript
application/pdf
Language
en_US
Relation
en_US AITR-963
Item sets
AI Technical Reports (1964 - 2004)