File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TPAMI.2011.112
- Scopus: eid_2-s2.0-84055212058
- PMID: 21646680
- WOS: WOS:000298105500014
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Toward a practical face recognition system: Robust alignment and illumination by sparse representation
Title | Toward a practical face recognition system: Robust alignment and illumination by sparse representation |
---|---|
Authors | |
Keywords | error correction face alignment Face recognition illumination variation occlusion and corruption sparse representation validation and outlier rejection |
Issue Date | 2012 |
Citation | IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, v. 34, n. 2, p. 372-386 How to Cite? |
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. © 2012 IEEE. |
Persistent Identifier | http://hdl.handle.net/10722/326880 |
ISSN | 2023 Impact Factor: 20.8 2023 SCImago Journal Rankings: 6.158 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wagner, Andrew | - |
dc.contributor.author | Wright, John | - |
dc.contributor.author | Ganesh, Arvind | - |
dc.contributor.author | Zhou, Zihan | - |
dc.contributor.author | Mobahi, Hossein | - |
dc.contributor.author | Ma, Yi | - |
dc.date.accessioned | 2023-03-31T05:27:11Z | - |
dc.date.available | 2023-03-31T05:27:11Z | - |
dc.date.issued | 2012 | - |
dc.identifier.citation | IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, v. 34, n. 2, p. 372-386 | - |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.uri | http://hdl.handle.net/10722/326880 | - |
dc.description.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. © 2012 IEEE. | - |
dc.language | eng | - |
dc.relation.ispartof | IEEE Transactions on Pattern Analysis and Machine Intelligence | - |
dc.subject | error correction | - |
dc.subject | face alignment | - |
dc.subject | Face recognition | - |
dc.subject | illumination variation | - |
dc.subject | occlusion and corruption | - |
dc.subject | sparse representation | - |
dc.subject | validation and outlier rejection | - |
dc.title | Toward a practical face recognition system: Robust alignment and illumination by sparse representation | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TPAMI.2011.112 | - |
dc.identifier.pmid | 21646680 | - |
dc.identifier.scopus | eid_2-s2.0-84055212058 | - |
dc.identifier.volume | 34 | - |
dc.identifier.issue | 2 | - |
dc.identifier.spage | 372 | - |
dc.identifier.epage | 386 | - |
dc.identifier.isi | WOS:000298105500014 | - |