International Journal of Computer Vision

, Volume 38, Issue 1, pp 15–33

A Trainable System for Object Detection

  • Constantine Papageorgiou
  • Tomaso Poggio
Article

DOI: 10.1023/A:1008162616689

Cite this article as:
Papageorgiou, C. & Poggio, T. International Journal of Computer Vision (2000) 38: 15. doi:10.1023/A:1008162616689

Abstract

This paper presents a general, trainable system for object detection in unconstrained, cluttered scenes. The system derives much of its power from a representation that describes an object class in terms of an overcomplete dictionary of local, oriented, multiscale intensity differences between adjacent regions, efficiently computable as a Haar wavelet transform. This example-based learning approach implicitly derives a model of an object class by training a support vector machine classifier using a large set of positive and negative examples. We present results on face, people, and car detection tasks using the same architecture. In addition, we quantify how the representation affects detection performance by considering several alternate representations including pixels and principal components. We also describe a real-time application of our person detection system as part of a driver assistance system.

computer visionmachine learningpattern recognitionpeople detectionface detectionear detection

Copyright information

© Kluwer Academic Publishers 2000

Authors and Affiliations

  • Constantine Papageorgiou
    • 1
  • Tomaso Poggio
    • 1
  1. 1.Center for Biological and Computational Learning, Artificial Intelligence LaboratoryMITCambridgeUSA