HOG active appearance models

Antonakos, Epameinondas; Alabort-i-Medina, Joan; Tzimiropoulos, Georgios; Zafeiriou, Stefanos

Abstract

We propose the combination of dense Histogram of Oriented Gradients (HOG) features with Active Appearance Models (AAMs). We employ the efficient Inverse Compositional optimization technique and show results for the task of face fitting. By taking advantage of the descriptive characteristics of HOG features, we build robust and accurate AAMs that generalize well to unseen faces with illumination, identity, pose and occlusion variations. Our experiments on challenging in-the-wild databases show that HOG AAMs significantly outperform current state-of-the-art results of discriminative methods trained on larger databases.

Citation

Antonakos, E., Alabort-i-Medina, J., Tzimiropoulos, G., & Zafeiriou, S. (2014, October). HOG active appearance models. Presented at 2014 IEEE International Conference on Image Processing (ICIP), Paris, France

• Presentation Conference Type: Edited Proceedings
• Conference Name: 2014 IEEE International Conference on Image Processing (ICIP)
• Start Date: Oct 27, 2014
• End Date: Oct 30, 2014
• Acceptance Date: Jul 3, 2014
• Online Publication Date: Jan 29, 2015
• Publication Date: Oct 27, 2014
• Deposit Date: Jan 29, 2016
• Publicly Available Date: Jan 29, 2016
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• ISBN: 9781479957521
• DOI: https://doi.org/10.1109/ICIP.2014.7025044
• Keywords: Active appearance models, Histogram of orientated gradients, Inverse compositional optimization
• Public URL: https://nottingham-repository.worktribe.com/output/994146
• Publisher URL: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7025044&punumber%3D6992914%26filter%3DAND%28p_IS_Number%3A7024995%29%26pageNumber%3D2
• Additional Information: © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; ; Published in: IEEE International Conference on Image Processing, 2014 (ICIP 2014), IEEE, 2014, ISBN 9781479957521.; doi: 10.1109/ICIP.2014.7025044
• Contract Date: Jan 29, 2016