Active Orientation Models for Face Alignment In-the-Wild

Georgios Tzimiropoulos,Stefanos P Zafeiriou,Joan Alabort-I-Medina,Maja Pantic

doi:10.1109/tifs.2014.2361018

Georgios Tzimiropoulos, Stefanos P Zafeiriou + Show 2 more

Open Access

https://doi.org/10.1109/tifs.2014.2361018

Copy DOI

Abstract

We present Active Orientation Models (AOMs), generative models of facial shape and appearance, which extend the well-known paradigm of Active Appearance Models (AAMs) for the case of generic face alignment under unconstrained conditions. Robustness stems from the fact that the proposed AOMs employ a statistically robust appearance model based on the principal components of image gradient orientations. We show that when incorporated within standard optimization frameworks for AAM learning and fitting, this kernel Principal Component Analysis results in robust algorithms for model fitting. At the same time, the resulting optimization problems maintain the same computational cost. As a result, the main similarity of AOMs with AAMs is the computational complexity. In particular, the project-out version of AOMs is as computationally efficient as the standard project-out inverse compositional algorithm, which is admittedly one of the fastest algorithms for fitting AAMs. We verify experimentally that: 1) AOMs generalize well to unseen variations and 2) outperform all other state-of-the-art AAM methods considered by a large margin. This performance improvement brings AOMs at least in par with other contemporary methods for face alignment. Finally, we provide MATLAB code at http://ibug.doc.ic.ac.uk/resources.

Highlights

B ECAUSE of their numerous applications in HCI, face analysis/recognition and medical imaging, the problems of learning and fitting deformable models have been the focus of cutting edge research in computer vision and machine learning for more than two decades
Main results. (a) Models: We propose Active Orientation Model, a generative deformable model that uses a statistically robust appearance model based on the principal components of image gradient orientations
AOMs employ a statistically robust appearance model based on the principal components of image gradient orientations

Summary

Introduction

B ECAUSE of their numerous applications in HCI, face analysis/recognition and medical imaging, the problems of learning and fitting deformable models have been the focus of cutting edge research in computer vision and machine learning for more than two decades. These problems can be summarized as follows: Learning a deformable model consists of (a) annotating (typically manually) a set of points (or landmarks) over a set of training images capturing an object of interest (e.g. faces), (b) learning a shape model (or point distribution model) which effectively. The associate editor coordinating the review of this manuscript and approving it for publication was Prof.

Objectives

Results

Conclusion