Open Access

A Probabilistic Model for Face Transformation with Application to Person Identification

EURASIP Journal on Advances in Signal Processing20042004:821283

https://doi.org/10.1155/S1110865704308012

Received: 30 October 2002

Published: 21 April 2004

Abstract

A novel approach for content-based image retrieval and its specialization to face recognition are described. While most face recognition techniques aim at modeling faces, our goal is to model the transformation between face images of the same person. As a global face transformation may be too complex to be modeled directly, it is approximated by a collection of local transformations with a constraint that imposes consistency between neighboring transformations. Local transformations and neighborhood constraints are embedded within a probabilistic framework using two-dimensional hidden Markov models (2D HMMs). We further introduce a new efficient technique, called turbo-HMM (T-HMM) for approximating intractable 2D HMMs. Experimental results on a face identification task show that our novel approach compares favorably to the popular eigenfaces and fisherfaces algorithms.

Keywords

face recognitionimage indexingface transformationhidden Markov models

Authors’ Affiliations

(1)
Multimedia Communications Department, Institut Eurécom
(2)
Department of Electrical and Computer Engineering, University of California

Copyright

© Perronnin et al. 2004