Rapid Object Recognition from Discriminative Regions of Interest

Gerald Fritz, Christin Seifert, Lucas Paletta, Horst Bischof

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

11 Citations (Scopus)
24 Downloads (Pure)


Object recognition and detection represent a relevant component in cognitive computer vision systems, such as in robot vision, intelligent video surveillance systems, or multimodal interfaces. Object identification from local information has recently been investigated with respect to its potential for robust recognition, e.g., in case of partial object occlusions, scale variation, noise, and background clutter in detection tasks. This work contributes to this research by a thorough analysis of the discriminative power of local appearance patterns and by proposing to exploit local information content to model object representation and recognition. We identify discriminative regions in the object views from a posterior entropy measure, and then derive object models from selected discriminative local patterns. For recognition, we determine rapid attentive search for locations of high information content from learned decision trees. The recognition system is evaluated by various degrees of partial occlusion and Gaussian image noise, resulting in highly robust recognition even in the presence of severe occlusion effects.
Original languageEnglish
Title of host publicationAAAI'04
Subtitle of host publicationProceedings of the 19th National Conference on Artifical Intelligence
EditorsGeorge Ferguson, Deborah McGuinness
Number of pages6
ISBN (Print)0-262-51183-5
Publication statusPublished - 2004
Externally publishedYes
Event19th National Conference on Artificial Intelligence, AAAI 2004 - San Jose Convention Center, San Jose, United States
Duration: 25 Jul 200429 Jul 2004
Conference number: 19


Conference19th National Conference on Artificial Intelligence, AAAI 2004
Abbreviated titleAAAI
Country/TerritoryUnited States
CitySan Jose


Dive into the research topics of 'Rapid Object Recognition from Discriminative Regions of Interest'. Together they form a unique fingerprint.

Cite this