International Journal of Computer Vision

, Volume 61, Issue 1, pp 55–79

Pictorial Structures for Object Recognition

  • Pedro F. Felzenszwalb
  • Daniel P. Huttenlocher
Article

DOI: 10.1023/B:VISI.0000042934.15159.49

Cite this article as:
Felzenszwalb, P.F. & Huttenlocher, D.P. International Journal of Computer Vision (2005) 61: 55. doi:10.1023/B:VISI.0000042934.15159.49

Abstract

In this paper we present a computationally efficient framework for part-based modeling and recognition of objects. Our work is motivated by the pictorial structure models introduced by Fischler and Elschlager. The basic idea is to represent an object by a collection of parts arranged in a deformable configuration. The appearance of each part is modeled separately, and the deformable configuration is represented by spring-like connections between pairs of parts. These models allow for qualitative descriptions of visual appearance, and are suitable for generic recognition problems. We address the problem of using pictorial structure models to find instances of an object in an image as well as the problem of learning an object model from training examples, presenting efficient algorithms in both cases. We demonstrate the techniques by learning models that represent faces and human bodies and using the resulting models to locate the corresponding objects in novel images.

part-based object recognitionstatistical modelsenergy minimization

Copyright information

© Kluwer Academic Publishers 2005

Authors and Affiliations

  • Pedro F. Felzenszwalb
    • 1
  • Daniel P. Huttenlocher
    • 2
  1. 1.Artificial Intelligence LabMassachusetts Institute of TechnologyUSA
  2. 2.Computer Science DepartmentCornell UniversityUSA