Object class recognition by boosting a part-based model

Aharon Bar-Hillel, Tomer Hertz, Daphna Weinshall

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

34 Scopus citations

Abstract

We propose a new technique for object class recognition, which learns a generative appearance model in a discriminative manner. The technique is based on the intermediate representation of an image as a set of patches, which are extracted using an interest point detector. The learning problem becomes an instance of supervised learning from sets of unordered features. In order to solve this problem, we designed a classifier based on a simple, part based, generative object model. Only the appearance of each part is modeled. When learning the model parameters, we use a discriminative boosting algorithm which minimizes the loss of the training error directly. The models thus learnt have clear probabilistic semantics, and also maintain good classification performance. The performance of the algorithm has been tested using publicly available benchmark data, and shown to be comparable to other state of the art algorithms for this task; our main advantage in these comparisons is speed (order of magnitudes faster) and scalability.

Original languageEnglish
Title of host publicationProceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
PublisherIEEE Computer Society
Pages702-709
Number of pages8
ISBN (Print)0769523722, 9780769523729
DOIs
StatePublished - 1 Jan 2005
Externally publishedYes
Event2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 - San Diego, CA, United States
Duration: 20 Jun 200525 Jun 2005

Publication series

NameProceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
VolumeI

Conference

Conference2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
Country/TerritoryUnited States
CitySan Diego, CA
Period20/06/0525/06/05

Fingerprint

Dive into the research topics of 'Object class recognition by boosting a part-based model'. Together they form a unique fingerprint.

Cite this