Abstract
Among various biometrics measures used in human identification, face recognition, has the distinct advantage of not requiring the subjects collaboration. Hyperspectral data constitute a natural choice for expanding face recognition image fusion, especially since it may provide information beyond the normal visible range, thus exceeding the normal human sensing. In this paper we investigate algorithms that improve face recognition by extracting the 'best bands' according to various criteria such as decorrelation and statistical independence. The work expands on previous band extraction results and has the distinct advantage of being one of the first that combines spatial information (i.e. face characteristics) with spectral information.
Original language | English |
---|---|
Title of host publication | Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV |
Volume | 7334 |
DOIs | |
State | Published - 14 Sep 2009 |
Event | Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV - Orlando, FL, United States Duration: 13 Apr 2009 → 16 Apr 2009 |
Other
Other | Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV |
---|---|
Country/Territory | United States |
City | Orlando, FL |
Period | 13/04/09 → 16/04/09 |
Keywords
- Face recognition
- Feature extraction
- Hyperspectral data