Object class recognition by unsupervised scale-invariant learning

R. Fergus, P. Perona, A. Zisserman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constellations of parts. A probabilistic representation is used for all aspects of the object: shape, appearance, occlusion and relative scale. An entropy-based feature detector is used to select regions and their scale within the image. In learning the parameters of the scale-invariant object model are estimated. This is done using expectation-maximization in a maximum-likelihood setting. In recognition, this model is used in a Bayesian manner to classify images. The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2
StatePublished - 2003
Event2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Madison, WI, United States
Duration: Jun 18 2003Jun 20 2003

Other

Other2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
CountryUnited States
CityMadison, WI
Period6/18/036/20/03

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Software
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Object class recognition by unsupervised scale-invariant learning'. Together they form a unique fingerprint.

Cite this