AVBPA 1999, 2nd international Conference on Audio-and Video-based Biometric Person Authentication, March 22-23, 1999, Washington, USA
This paper introduces the use of Hidden Markov Models (HMM) as an alternative to techniques classically used for face detection. Our aim is to locate faces in colour images of a video sequence in view to indexing. The use of HMM in pattern recognition is first briefly reviewed and the mapping of these models onto our problem is presented. Pseudo two-dimensional HMM are presented and shown to be efficient and well-suited tools for performing face detection in a context where no constraints on face orientation are given. Issues about efficient face modelling are discussed and illustrated with practical examples.
Type:
Conference
City:
Washington
Date:
1999-03-22
Department:
Data Science
Eurecom Ref:
162
Copyright:
© Springer. Personal use of this material is permitted. The definitive version of this paper was published in AVBPA 1999, 2nd international Conference on Audio-and Video-based Biometric Person Authentication, March 22-23, 1999, Washington, USA and is available at :
See also:
