Robust Statistical Face Frontalization
Open Access
- 1 December 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3871-3879
- https://doi.org/10.1109/iccv.2015.441
Abstract
Recently, it has been shown that excellent results can be achieved in both facial landmark localization and pose-invariant face recognition. These breakthroughs are attributed to the efforts of the community to manually annotate facial images in many different poses and to collect 3D facial data. In this paper, we propose a novel method for joint frontal view reconstruction and landmark localization using a small set of frontal images only. By observing that the frontal facial image is the one having the minimum rank of all different poses, an appropriate 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, involving the minimization of the nuclear norm and the matrix l1 norm is solved. The proposed method is assessed in frontal face reconstruction, face landmark localization, pose-invariant face recognition, and face verification in unconstrained conditions. The relevant experiments have been conducted on 8 databases. The experimental results demonstrate the effectiveness of the proposed method in comparison to the state-of-the-art methods for the target problems.Keywords
This publication has 35 references indexed in Scilit:
- Music Genre Classification via Joint Sparse Low-Rank Representation of Audio FeaturesIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- Generic Active Appearance Models RevisitedLecture Notes in Computer Science, 2013
- TILT: Transform Invariant Low-Rank TexturesInternational Journal of Computer Vision, 2012
- Robust principal component analysis?Journal of the ACM, 2011
- Multi-PIEImage and Vision Computing, 2010
- A Singular Value Thresholding Algorithm for Matrix CompletionSIAM Journal on Optimization, 2010
- Cat Head Detection - How to Effectively Exploit Shape and Texture FeaturesLecture Notes in Computer Science, 2008
- Active Appearance Models RevisitedInternational Journal of Computer Vision, 2004
- The FERET evaluation methodology for face-recognition algorithmsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Active Shape Models-Their Training and ApplicationComputer Vision and Image Understanding, 1995