From pixels to response maps: discriminative image filtering for face alignment in the wild

Asthana, A. and Zafeiriou, S. and Tzimiropoulos, Georgios and Cheng, S. and Pantic, M. (2015) From pixels to response maps: discriminative image filtering for face alignment in the wild. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37 (6). pp. 1312-1320. ISSN 0162-8828

Documents
From pixels to response maps: discriminative image filtering for face alignment in the wild

Request a copy
__ddat02_staffhome_jpartridge_tzimiroTPAMI15.pdf
[img]
[Download]
[img] PDF
__ddat02_staffhome_jpartridge_06919301.pdf - Whole Document
Restricted to Repository staff only

1MB
[img]
Preview
PDF
__ddat02_staffhome_jpartridge_tzimiroTPAMI15.pdf - Whole Document

6MB
Item Type:Article
Item Status:Live Archive

Abstract

We propose a face alignment framework that relies on the texture model generated by the responses of discriminatively trained part-based filters. Unlike standard texture models built from pixel intensities or responses generated by generic filters (e.g. Gabor), our framework has two important advantages. First, by virtue of discriminative training, invariance to external variations (like identity, pose, illumination and expression) is achieved. Second, we show that the responses generated by discriminatively trained filters (or patch-experts) are sparse and can be modeled using a very small number of parameters. As a result, the optimization methods based on the proposed texture model can better cope with unseen variations. We illustrate this point by formulating both part-based and holistic approaches for generic face alignment and show that our framework outperforms the state-of-the-art on multiple "wild" databases. The code and dataset annotations are available for research purposes from http://ibug.doc.ic.ac.uk/resources. © 2014 IEEE.

Keywords:Alignment, Face recognition, Gabor filters, Textures, Active appearance models, Constrained local models, Discriminative training, Face alignment, Facial landmark detection, Holistic approach, Optimization method, Pixel intensities, Pixels, JCNotOpen
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:17528
Deposited On:29 May 2015 09:26

Repository Staff Only: item control page