HOG active appearance models

Antonakos, Epameinondas and Alabort-i-Medina, Joan and Tzimiropoulos, Georgios and Zafeiriou, Stefanos (2014) HOG active appearance models. In: 2014 IEEE International Conference on Image Processing (ICIP), 27-30 Oct 2014, Paris, France.

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (12MB) | Preview

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.

Item Type: Conference or Workshop Item (Paper)
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.
Keywords: Active appearance models, Histogram of orientated gradients, Inverse compositional optimization
Schools/Departments: University of Nottingham UK Campus > Faculty of Science > School of Computer Science
Depositing User: Tzimiropoulos, Yorgos
Date Deposited: 29 Jan 2016 11:12
Last Modified: 14 Sep 2016 01:55
URI: http://eprints.nottingham.ac.uk/id/eprint/31441

Actions (Archive Staff Only)

Edit View Edit View