Skip to main content

Research Repository

Advanced Search

Cascaded regression with sparsified feature covariance matrix for facial landmark detection

S�nchez Lozano, Enrique; Martinez, Brais; Valstar, Michel F.

Authors

Enrique S�nchez Lozano

Brais Martinez

Michel F. Valstar



Abstract

This paper explores the use of context on regression-based methods for facial landmarking. Regression based methods have revolutionised facial landmarking solutions. In particular those that implicitly infer the whole shape of a structured object have quickly become the state-of-the-art. The most notable exemplar is the Supervised Descent Method (SDM). Its main characteristics are the use of the cascaded regression approach, the use of the full appearance as the inference input, and the aforementioned aim to directly predict the full shape. In this article we argue that the key aspects responsible for the success of SDM are the use of cascaded regression and the avoidance of the constrained optimisation problem that characterised most of the previous approaches.We show that, surprisingly, it is possible to achieve comparable or superior performance using only landmark-specific predictors, which are linearly combined. We reason that augmenting the input with too much context (of which using the full appearance is the extreme case) can be harmful. In fact, we experimentally found that there is a relation between the data variance and the benefits of adding context to the input. We finally devise a simple greedy procedure that makes use of this fact to obtain superior performance to the SDM, while maintaining the simplicity of the algorithm. We show extensive results both for intermediate stages devised to prove the main aspects of the argumentative line, and to validate the overall performance of two models constructed based on these considerations.

Citation

Sánchez Lozano, E., Martinez, B., & Valstar, M. F. (2016). Cascaded regression with sparsified feature covariance matrix for facial landmark detection. Pattern Recognition Letters, 73, 19-25. https://doi.org/10.1016/j.patrec.2015.11.014

Journal Article Type Article
Acceptance Date Nov 8, 2015
Online Publication Date Jan 13, 2016
Publication Date 2016-04
Deposit Date Jan 21, 2016
Publicly Available Date Mar 28, 2024
Journal Pattern Recognition Letters
Print ISSN 0167-8655
Electronic ISSN 0167-8655
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 73
Pages 19-25
DOI https://doi.org/10.1016/j.patrec.2015.11.014
Public URL https://nottingham-repository.worktribe.com/output/772927
Publisher URL http://www.sciencedirect.com/science/article/pii/S0167865515004006
Additional Information This article is maintained by: Elsevier; Article Title: Cascaded regression with sparsified feature covariance matrix for facial landmark detection; Journal Title: Pattern Recognition Letters; CrossRef DOI link to publisher maintained version: https://doi.org/10.1016/j.patrec.2015.11.014; Content Type: article; Copyright: Copyright © 2015 Elsevier B.V. All rights reserved.

Files





You might also like



Downloadable Citations