 |
Face Recognition with APCA in Variant Illuminations
Chen, S., Lovell, B. C. and Sun, S. (2002). Face Recognition with APCA in Variant Illuminations. In: Chandran, V., Proceedings of the Fourth Australasian Workshop on Signal Processing and Applications 2002. Fourth Australasian Workshop on Signal Processing and Applications 2002, Brisbane, (9-12). 17-18 December, 2002.
|
|
| |
| Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials) |
| Name |
Description |
MIMEType |
Size |
Downloads |
OS1.pdf
|
OS1.pdf |
application/pdf |
674.24KB |
559 |
| Author(s) |
Chen, S.
Lovell, B. C.
Sun, S.
|
| Title of paper |
Face Recognition with APCA in Variant Illuminations
|
| Conference name |
Fourth Australasian Workshop on Signal Processing and Applications 2002
|
| Conference location |
Brisbane
|
| Conference dates |
17-18 December, 2002
|
| Proceedings title |
Proceedings of the Fourth Australasian Workshop on Signal Processing and Applications 2002
|
| Editor(s) |
Chandran, V.
|
| Place published |
Brisbane
|
| Publisher |
Queensland University of Technology
|
| Publication date |
2002
|
| Volume number |
1
|
| Issue number |
1
|
| Start page |
9
|
| End page |
12
|
| Total pages |
4
|
| Collection year |
2002
|
| Language |
eng
|
| Abstract/Summary |
PCA (Principal Component Analysis) and FLD (Fisher Linear Discriminant) methods for face recognition perform well in controlled laboratory conditions but encounter difficulties under variant illuminations or facial expressions. We propose a new method called Affine PCA to overcome these limitations with respect to lighting variations. This technique distinguishes contributions between features in the affine PCA derived eigenspace according to the correlation between eigenfeatures and illumination. This technique is applied to the Asian Face Image Database PF01, which consists of 535 images - 107 faces under 5 different illuminations. We perform three-fold cross-validation on this database to show that the proposed Affine PCA method achieves 96% recognition rate compared to standard PCA and FLD with only 51% and 65% respectively.
|
| Subjects |
280208 Computer Vision
E1
700199 Computer software and services not elsewhere classified
|
| Keyword(s) |
iris-research
face recognition
Principal Component Analysis
Fisher Linear Discriminant
eigenfeatures
|
|
|
|
