DMCA
Towards a Practical Face Recognition System: Robust Alignment and Illumination by Sparse Representation (2010)
| Citations: | 108 - 10 self |
BibTeX
@MISC{Wagner10towardsa,
author = {Andrew Wagner and John Wright and Arvind Ganesh and Zihan Zhou and Hossein Mobahi and Yi Ma},
title = {Towards a Practical Face Recognition System: Robust Alignment and Illumination by Sparse Representation},
year = {2010}
}
Share
 |
 |
 |
 |
||
OpenURL
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 datasets 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.
Keyphrases
sparse representation practical face recognition system robust alignment test image training image image misalignment practical testing condition illumination variation complete face recognition system frontal image uncontrolled illumination alignment algorithm simple face recognition system public data set high degree public face datasets partial occlusion real recognition system contemporary face recognition algorithm work algorithm work projector-based training acquisition system realistic condition enough illumination variation frontal training image test face image
