The Community for Technology Leaders
Green Image
Issue No. 02 - February (2012 vol. 34)
ISSN: 0162-8828
pp: 372-386
Zihan Zhou , Dept. of Electr. & Comput. Eng., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
A. Ganesh , Dept. of Electr. & Comput. Eng., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
J. Wright , Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
A. Wagner , Dept. of Electr. & Comput. Eng., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
H. Mobahi , Comput. Sci. Dept., Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA
Yi Ma , Dept. of Electr. & Comput. Eng., Univ. of Illinois at Urbana- Champaign, Urbana, IL, USA
ABSTRACT
Many classic and contemporary face recognition algorithms work well on public data sets, but degrade sharply when they are used in a real recognition system. This is mostly due to the difficulty of simultaneously handling variations in illumination, image misalignment, and occlusion in the test image. We consider a scenario where the training images are well controlled and test images are only loosely controlled. We propose a conceptually simple face recognition system that achieves a high degree of robustness and stability to illumination variation, image misalignment, and partial occlusion. The system uses tools from sparse representation to align a test face image to a set of frontal training images. The region of attraction of our alignment algorithm is computed empirically for public face data sets such as Multi-PIE. We demonstrate how to capture a set of training images with enough illumination variation that they span test images taken under uncontrolled illumination. In order to evaluate how our algorithms work under practical testing conditions, we have implemented a complete face recognition system, including a projector-based training acquisition system. Our system can efficiently and effectively recognize faces under a variety of realistic conditions, using only frontal images under the proposed illuminations as training.
INDEX TERMS
image representation, face recognition, partial occlusion, face recognition system, robust alignment, robust illumination, sparse representation, public data sets, handling variations, image misalignment, illumination variation, Lighting, Face recognition, Image recognition, Databases, validation and outlier rejection., Face recognition, face alignment, illumination variation, occlusion and corruption, sparse representation, error correction
CITATION
Zihan Zhou, A. Ganesh, J. Wright, A. Wagner, H. Mobahi, Yi Ma, "Toward a Practical Face Recognition System: Robust Alignment and Illumination by Sparse Representation", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 34, no. , pp. 372-386, February 2012, doi:10.1109/TPAMI.2011.112
107 ms
(Ver 3.3 (11022016))