Generic active appearance models revisited

The proposed Active Orientation Models (AOMs) are generative models of facial shape and appearance. Their main differences with the well-known paradigm of Active Appearance Models (AAMs) are (i) they use a different statistical model of appearance, (ii) they are accompanied by a robust algorithm for...

Full description

Bibliographic Details
Main Authors: Tzimiropoulos, Georgios, Alabort-i-Medina, Joan, Zafeiriou, Stefanos, Pantic, Maja
Format: Article
Published: Springer 2013
Online Access:https://eprints.nottingham.ac.uk/31430/
_version_ 1848794199776821248
author Tzimiropoulos, Georgios
Alabort-i-Medina, Joan
Zafeiriou, Stefanos
Pantic, Maja
author_facet Tzimiropoulos, Georgios
Alabort-i-Medina, Joan
Zafeiriou, Stefanos
Pantic, Maja
author_sort Tzimiropoulos, Georgios
building Nottingham Research Data Repository
collection Online Access
description The proposed Active Orientation Models (AOMs) are generative models of facial shape and appearance. Their main differences with the well-known paradigm of Active Appearance Models (AAMs) are (i) they use a different statistical model of appearance, (ii) they are accompanied by a robust algorithm for model fitting and parameter estimation and (iii) and, most importantly, they generalize well to unseen faces and variations. Their main similarity is computational complexity. The project-out version of AOMs is as computationally efficient as the standard project-out inverse compositional algorithm which is admittedly the fastest algorithm for fitting AAMs. We show that not only does the AOM generalize well to unseen identities, but also it outperforms state-of-the-art algorithms for the same task by a large margin. Finally, we prove our claims by providing Matlab code for reproducing our experiments.
first_indexed 2025-11-14T19:12:24Z
format Article
id nottingham-31430
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:12:24Z
publishDate 2013
publisher Springer
recordtype eprints
repository_type Digital Repository
spelling nottingham-314302020-05-04T20:20:54Z https://eprints.nottingham.ac.uk/31430/ Generic active appearance models revisited Tzimiropoulos, Georgios Alabort-i-Medina, Joan Zafeiriou, Stefanos Pantic, Maja The proposed Active Orientation Models (AOMs) are generative models of facial shape and appearance. Their main differences with the well-known paradigm of Active Appearance Models (AAMs) are (i) they use a different statistical model of appearance, (ii) they are accompanied by a robust algorithm for model fitting and parameter estimation and (iii) and, most importantly, they generalize well to unseen faces and variations. Their main similarity is computational complexity. The project-out version of AOMs is as computationally efficient as the standard project-out inverse compositional algorithm which is admittedly the fastest algorithm for fitting AAMs. We show that not only does the AOM generalize well to unseen identities, but also it outperforms state-of-the-art algorithms for the same task by a large margin. Finally, we prove our claims by providing Matlab code for reproducing our experiments. Springer 2013 Article PeerReviewed Tzimiropoulos, Georgios, Alabort-i-Medina, Joan, Zafeiriou, Stefanos and Pantic, Maja (2013) Generic active appearance models revisited. Lecture Notes in Computer Science, 7726 . pp. 650-663. ISSN 0302-9743 http://link.springer.com/chapter/10.1007/978-3-642-37431-9_50 doi:10.1007/978-3-642-37431-9_50 doi:10.1007/978-3-642-37431-9_50
spellingShingle Tzimiropoulos, Georgios
Alabort-i-Medina, Joan
Zafeiriou, Stefanos
Pantic, Maja
Generic active appearance models revisited
title Generic active appearance models revisited
title_full Generic active appearance models revisited
title_fullStr Generic active appearance models revisited
title_full_unstemmed Generic active appearance models revisited
title_short Generic active appearance models revisited
title_sort generic active appearance models revisited
url https://eprints.nottingham.ac.uk/31430/
https://eprints.nottingham.ac.uk/31430/
https://eprints.nottingham.ac.uk/31430/