A Probabilistic Model for Face Transformation with Application to Person Identification
- PDF / 953,999 Bytes
- 12 Pages / 600 x 792 pts Page_size
- 15 Downloads / 165 Views
A Probabilistic Model for Face Transformation with Application to Person Identification Florent Perronnin Multimedia Communications Department, Institut Eur´ecom, BP 193, 06904 Sophia Antipolis Cedex, France Email: [email protected]
Jean-Luc Dugelay Multimedia Communications Department, Institut Eur´ecom, BP 193, 06904 Sophia Antipolis Cedex, France Email: [email protected]
Kenneth Rose Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA 93106-9560, USA Email: [email protected] Received 30 October 2002; Revised 23 June 2003 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 and phrases: face recognition, image indexing, face transformation, hidden Markov models.
1.
INTRODUCTION
Pattern classification is concerned with the general problem of inferring classes or “categories” from observations [1]. The success of a pattern classification system is largely dependent on the quality of its stochastic model, which generally models the generation of observations, to capture the intraclass variability. Face recognition is a challenging pattern classification problem [2, 3] as face images of the same person are subject to variations in facial expression, pose, illumination conditions, presence or absence of eyeglasses and facial hair, and so forth. Most face recognition algorithms attempt to build for each person P a face model ᏹ p (the stochastic source of the system) which is designed to describe as accurately as possible his/her intraface variability. This paper introduces a novel approach for contentbased image retrieval, which is applied to face identification and whose stochastic model focuses on the relation between observations of the same class rather than the generation process. Here we attempt to model a transformation be-
tween face images of the same person. If ᏲT and ᏲQ are, respectively, template and query images and if ᏹ is the probabilistic transformation model, then our goal is to estimate P(ᏲT |ᏲQ , ᏹ). An important assumption made here is that the intraclass variability is the same for all classes and thus, ᏹ can be shared by all individuals. As the global face transformation may be too complex to be modeled directly, the basic idea
Data Loading...
