International Journal of Computer Vision

, Volume 57, Issue 2, pp 137–154

Robust Real-Time Face Detection

  • Paul Viola
  • Michael J. Jones
Article

DOI: 10.1023/B:VISI.0000013087.49260.fb

Cite this article as:
Viola, P. & Jones, M.J. International Journal of Computer Vision (2004) 57: 137. doi:10.1023/B:VISI.0000013087.49260.fb

Abstract

This paper describes a face detection framework that is capable of processing images extremely rapidly while achieving high detection rates. There are three key contributions. The first is the introduction of a new image representation called the “Integral Image” which allows the features used by our detector to be computed very quickly. The second is a simple and efficient classifier which is built using the AdaBoost learning algorithm (Freund and Schapire, 1995) to select a small number of critical visual features from a very large set of potential features. The third contribution is a method for combining classifiers in a “cascade” which allows background regions of the image to be quickly discarded while spending more computation on promising face-like regions. A set of experiments in the domain of face detection is presented. The system yields face detection performance comparable to the best previous systems (Sung and Poggio, 1998; Rowley et al., 1998; Schneiderman and Kanade, 2000; Roth et al., 2000). Implemented on a conventional desktop, face detection proceeds at 15 frames per second.

face detection boosting human sensing 

Copyright information

© Kluwer Academic Publishers 2004

Authors and Affiliations

  • Paul Viola
    • 1
  • Michael J. Jones
    • 2
  1. 1.Microsoft ResearchOne Microsoft WayRedmondUSA
  2. 2.Mitsubishi Electric Research LaboratoryCambridgeUSA

Personalised recommendations