Feature-based Lucas-Kanade and Active Appearance Models

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

Abstract

Lucas-Kanade and Active Appearance Models are among the most commonly used methods for image alignment and facial fitting, respectively. They both utilize non-linear gradient descent, which is usually applied on intensity values. In this paper, we propose the employment of highly-descriptive, densely-sampled image features for both problems. We show that the strategy of warping the multi-channel dense feature image at each iteration is more beneficial than extracting features after warping the intensity image at each iteration. Motivated by this observation, we demonstrate robust and accurate alignment and fitting performance using a variety of powerful feature descriptors. Especially with the employment of HOG and SIFT features, our method significantly outperforms the current state-of-the-art results on in-the-wild databases.

Citation

Antonakos, E., Alabort-i-Medina, J., Tzimiropoulos, G., & Zafeiriou, S. P. (2015). Feature-based Lucas-Kanade and Active Appearance Models. IEEE Transactions on Image Processing, 24(9), https://doi.org/10.1109/TIP.2015.2431445

• Journal Article Type: Article
• Publication Date: May 8, 2015
• Deposit Date: Jan 29, 2016
• Publicly Available Date: Jan 29, 2016
• Journal: IEEE Transactions on Image Processing
• Print ISSN: 1057-7149
• Electronic ISSN: 1941-0042
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 24
• Issue: 9
• DOI: https://doi.org/10.1109/TIP.2015.2431445
• Public URL: https://nottingham-repository.worktribe.com/output/752403
• Publisher URL: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7104116
• Additional Information: (c) 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, 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 components of this work in other works.