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

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 advant...

Full description

Bibliographic Details
Main Authors: Asthana, Akshay, Zafeiriou, Stefanos, Tzimiropoulos, Georgios, Cheng, Shiyang, Pantic, Maja
Format: Article
Published: Institute of Electrical and Electronics Engineers 2014
Online Access:https://eprints.nottingham.ac.uk/31438/
_version_ 1848794202100465664
author Asthana, Akshay
Zafeiriou, Stefanos
Tzimiropoulos, Georgios
Cheng, Shiyang
Pantic, Maja
author_facet Asthana, Akshay
Zafeiriou, Stefanos
Tzimiropoulos, Georgios
Cheng, Shiyang
Pantic, Maja
author_sort Asthana, Akshay
building Nottingham Research Data Repository
collection Online Access
description 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. Firstly, by virtue of discriminative training, invariance to external variations (like identity, pose, illumination and expression) is achieved. Secondly, 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.
first_indexed 2025-11-14T19:12:26Z
format Article
id nottingham-31438
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:12:26Z
publishDate 2014
publisher Institute of Electrical and Electronics Engineers
recordtype eprints
repository_type Digital Repository
spelling nottingham-314382020-05-04T16:56:09Z https://eprints.nottingham.ac.uk/31438/ From pixels to response maps: discriminative image filtering for face alignment in the wild Asthana, Akshay Zafeiriou, Stefanos Tzimiropoulos, Georgios Cheng, Shiyang Pantic, Maja 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. Firstly, by virtue of discriminative training, invariance to external variations (like identity, pose, illumination and expression) is achieved. Secondly, 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. Institute of Electrical and Electronics Engineers 2014-10-09 Article PeerReviewed Asthana, Akshay, Zafeiriou, Stefanos, Tzimiropoulos, Georgios, Cheng, Shiyang and Pantic, Maja (2014) 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 http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6919301&tag=1 doi:10.1109/TPAMI.2014.2362142 doi:10.1109/TPAMI.2014.2362142
spellingShingle Asthana, Akshay
Zafeiriou, Stefanos
Tzimiropoulos, Georgios
Cheng, Shiyang
Pantic, Maja
From pixels to response maps: discriminative image filtering for face alignment in the wild
title From pixels to response maps: discriminative image filtering for face alignment in the wild
title_full From pixels to response maps: discriminative image filtering for face alignment in the wild
title_fullStr From pixels to response maps: discriminative image filtering for face alignment in the wild
title_full_unstemmed From pixels to response maps: discriminative image filtering for face alignment in the wild
title_short From pixels to response maps: discriminative image filtering for face alignment in the wild
title_sort from pixels to response maps: discriminative image filtering for face alignment in the wild
url https://eprints.nottingham.ac.uk/31438/
https://eprints.nottingham.ac.uk/31438/
https://eprints.nottingham.ac.uk/31438/