Return to search

Component based recognition of objects in an office environment

We present a component-based approach for recognizing objects under large pose changes. From a set of training images of a given object we extract a large number of components which are clustered based on the similarity of their image features and their locations within the object image. The cluster centers build an initial set of component templates from which we select a subset for the final recognizer. In experiments we evaluate different sizes and types of components and three standard techniques for component selection. The component classifiers are finally compared to global classifiers on a database of four objects.
Date28 November 2003
CreatorsMorgenstern, Christian, Heisele, Bernd
Source SetsM.I.T. Theses and Dissertation
Detected LanguageEnglish
Format12 p., 3572823 bytes, 962401 bytes, application/postscript, application/pdf
RelationAIM-2003-024, CBCL-232

Page generated in 0.0019 seconds