Imperial College London
Alternate

STEFANOS ZAFEIRIOU, PhD

Faculty of Engineering, Department of Computing

Professor in Machine Learning & Computer Vision
 
 
 
//

Contact

 

+44 (0)20 7594 8461s.zafeiriou Website CV

 
 
//

Location

 

375Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Sagonas:2016:10.1007/s11263-016-0920-7,
author = {Sagonas, C and Panagakis, Y and Zafeiriou, S and Pantic, M},
doi = {10.1007/s11263-016-0920-7},
journal = {International Journal of Computer Vision},
pages = {270--291},
title = {Robust statistical frontalization of human and animal faces},
url = {http://dx.doi.org/10.1007/s11263-016-0920-7},
volume = {122},
year = {2016}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - The unconstrained acquisition of facial data in real-world conditions may result in face images with significant pose variations, illumination changes, and occlusions, affecting the performance of facial landmark localization and recognition methods. In this paper, a novel method, robust to pose, illumination variations, and occlusions is proposed for joint face frontalization and landmark localization. Unlike the state-of-the-art methods for landmark localization and pose correction, where large amount of manually annotated images or 3D facial models are required, the proposed method relies on a small set of frontal images only. By observing that the frontal facial image of both humans and animals, is the one having the minimum rank of all different poses, a model which is able to jointly recover the frontalized version of the face as well as the facial landmarks is devised. To this end, a suitable optimization problem is solved, concerning minimization of the nuclear norm (convex surrogate of the rank function) and the matrix (Formula presented.) norm accounting for occlusions. The proposed method is assessed in frontal view reconstruction of human and animal faces, landmark localization, pose-invariant face recognition, face verification in unconstrained conditions, and video inpainting by conducting experiment on 9 databases. The experimental results demonstrate the effectiveness of the proposed method in comparison to the state-of-the-art methods for the target problems.
AU  - Sagonas,C
AU  - Panagakis,Y
AU  - Zafeiriou,S
AU  - Pantic,M
DO  - 10.1007/s11263-016-0920-7
EP  - 291
PY  - 2016///
SN  - 0920-5691
SP  - 270
TI  - Robust statistical frontalization of human and animal faces
T2  - International Journal of Computer Vision
UR  - http://dx.doi.org/10.1007/s11263-016-0920-7
UR  - http://hdl.handle.net/10044/1/38524
VL  - 122
ER  -
Download