Learning Based Automatic Face Annotation for Arbitrary Poses and Expressions from Frontal Images Only

Authors: Akshay Asthana, Roland Göcke, Novi Quadrianto, and Tom Gedeon

Presented by Akshay Asthana at the IEEE Computer Society Conference on Computer Vision and Pattern Recognition CVPR2009, Miami (FL), USA, 20-25 June 2009

Abstract

Statistical approaches for building non-rigid deformable models, such as the Active Appearance Model (AAM), have enjoyed great popularity in recent years, but typically require tedious manual annotation of training images. In this paper, a learning based approach for the automatic annotation of visually deformable objects from a single annotated frontal image is presented and demonstrated on the example of automatically annotating face images that can be used for building AAMs for fitting and tracking. This approach employs the idea of initially learning the correspondences between landmarks in a frontal image and a set of training images with a face in arbitrary poses. Using this learner, virtual images of unseen faces at any arbitrary pose for which the learner was trained can be reconstructed by predicting the new landmark locations and warping the texture from the frontal image. View-based AAMs are then built from the virtual images and used for automatically annotating unseen images, including images of different facial expressions, at any random pose within the maximum range spanned by the virtually reconstructed images. The approach is experimentally validated by automatically annotating face images from three different databases.

Download paper (844kB, PDF)
©2009 IEEE

Bibtex Entry

@INPROCEEDINGS{asthana_goecke_quadrianto_gedeon2009,
AUTHOR = {A. Asthana and R. Goecke and N. Quadrianto and T. Gedeon},
TITLE = {{Learning Based Automatic Face Annotation for Arbitrary Poses and Expressions from Frontal Images Only}},
BOOKTITLE = {{Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition CVPR 2009}},
PUBLISHER = {IEEE Computer Society},
ADDRESS = {Miami (FL), USA},
MONTH = jun,
YEAR = 2009,
NOTE = {}}

[Homepage] [Research] [Publications]

(c) Roland Göcke
Last modified: Fri Jul 10 23:07:17 AUS Eastern Normalzeit 2009