 |
Face Recognition with One Sample Image per Class
Chen, Shaokang and Lovell, Brian C. (2003). Face Recognition with One Sample Image per Class. In: Lovell, Brian C., Campbell, Duncan A., Fookes, Clinton B. and Maeder, Anthony J., Proceedings of the Eighth Australian and New Zealand Intelligent Information Systems Conference. Australian and New Zealand Intelligent Information Systems, Sydney, (83-88). 10-12 December.
|
|
| |
| Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials) |
| Name |
Description |
MIMEType |
Size |
Downloads |
paper131.pdf
|
paper131.pdf |
application/pdf |
566.87KB |
561 |
| Author(s) |
Chen, Shaokang
Lovell, Brian C.
|
| Title of paper |
Face Recognition with One Sample Image per Class
|
| Conference name |
Australian and New Zealand Intelligent Information Systems
|
| Conference location |
Sydney
|
| Conference dates |
10-12 December
|
| Proceedings title |
Proceedings of the Eighth Australian and New Zealand Intelligent Information Systems Conference
|
| Editor(s) |
Lovell, Brian C.
Campbell, Duncan A.
Fookes, Clinton B.
Maeder, Anthony J.
|
| Place published |
Brisbane
|
| Publisher |
Queensland University of Technology
|
| Publication date |
2003
|
| Volume number |
1
|
| Issue number |
1
|
| ISBN |
1-74107-039-2
|
| Start page |
83
|
| End page |
88
|
| Total pages |
6
|
| Language |
eng
|
| Abstract/Summary |
There are two main approaches for face recognition with variations in lighting conditions. One is to represent images with features that are insensitive to illumination in the first place. The other main approach is to construct a linear subspace for every class under the different lighting conditions. Both of these techniques are successfully applied to some extent in face recognition, but it is hard to extend them for recognition with variant facial expressions. It is observed that features insensitive to illumination are highly sensitive to expression variations, which result in face recognition with changes in both lighting conditions and expressions a difficult task. We propose a new method called Affine Principal Components Analysis in an attempt to solve both of these problems. This method extract features to construct a subspace for face representation and warps this space to achieve better class separation. The proposed technique is evaluated using face databases with both variable lighting and facial expressions. We achieve more than 90% accuracy for face recognition by using only one sample image per class.
|
| Subjects |
280208 Computer Vision
280203 Image Processing
280207 Pattern Recognition
|
| Keyword(s) |
iris-research
|
|
|
|
