Robust Face Alignment Based On Hierarchical Classifier Network

DMCA

Robust Face Alignment Based On Hierarchical Classifier Network (2006)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Li Zhang , Haizhou Ai , Shihong Lao

Venue:	Proc. ECCV Workshop Human-Computer Interaction
Citations:	3 - 0 self

BibTeX

@INPROCEEDINGS{Zhang06robustface,
    author = {Li Zhang and Haizhou Ai and Shihong Lao},
    title = {Robust Face Alignment Based On Hierarchical Classifier Network},
    booktitle = {Proc. ECCV Workshop Human-Computer Interaction},
    year = {2006}
}

OpenURL

Abstract

Abstract. Robust face alignment is crucial for many face processing applications. As face detection only gives a rough estimation of face region, one important problem is how to align facial shapes starting from this rough estimation, especially on face images with expression and pose changes. We propose a novel method of face alignment by building a hierarchical classifier network, connecting face detection and face alignment into a smooth coarse-to-fine procedure. Classifiers are trained to recognize feature textures in different scales from entire face to local patterns. A multi-layer structure is employed to organize the classifiers, which begins with one classifier at the first layer and gradually refines the localization of feature points by more classifiers in the following layers. A Bayesian framework is configured for the inference of the feature points between the layers. The boosted classifiers detects facial features discriminately from its local neighborhood, while the inference between thelayersconstrainsthesearchingspace. Extensive experiments are reported to show its accuracy and robustness. 1

Keyphrases

robust face alignment hierarchical classifier network rough estimation face alignment feature point face detection pose change feature texture multi-layer structure local pattern important problem smooth coarse-to-fine procedure following layer extensive experiment face image different scale facial shape local neighborhood face region many face processing application boosted classifier facial feature novel method first layer entire face bayesian framework

DMCA