Learning to Identify and Track Faces in Image Sequences

DMCA

Learning to Identify and Track Faces in Image Sequences (1997)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by G.J. Edwards , C.J. Taylor , T.F. Cootes , Wolfson Image , Analysis Unit , Department Of Medical Biophysics

Citations:

63 - 8 self

BibTeX

@MISC{Edwards97learningto,
    author = {G.J. Edwards and C.J. Taylor and T.F. Cootes and Wolfson Image and Analysis Unit and Department Of Medical Biophysics},
    title = {Learning to Identify and Track Faces in Image Sequences},
    year = {1997}
}

OpenURL

Abstract

We address the problem of robust face identification in the presence of pose, lighting, and expression variation. Previous approaches to the problem have assumed similar models of variation for each individual, estimated from pooled training data. We describe a method of updating a first order global estimate of identity by learning the classspecific correlation between the estimate and the residual variation during a sequence. This is integrated with an optimal tracking scheme, in which identity variation is decoupled from pose, lighting and expression variation. The method results in robust tracking and a more stable estimate of facial identity under changing conditions. 1 Introduction Locating and interpreting faces in images and image sequences is a difficult problem in machine vision, due to the inherent variability between and within individuals. The appearance of a face in an image varies with the identity of the individual, pose, lighting conditions, and deformations due to e...

Keyphrases

image sequence track face expression variation first order global estimate image varies robust tracking machine vision inherent variability facial identity introduction locating optimal tracking scheme residual variation difficult problem method result classspecific correlation robust face identification identity variation previous approach pooled training data similar model stable estimate

DMCA