Abstract
Face recognition performed in a controlled environment can be reduced to classical image retrieval/pattern recognition of frontal 2D images of a person. Current holistic appearance based methods require a high dimension feature space to cope with the problem. We, therefore, proposed a relatively low feature dimension scheme for the reduced face recognition problem; aggregated Gabor filter responses is employed to represent face images. Experiments have been done on two testing sets of a face image database from which the preprocessing and size of image differ; each set contains over 3,000 images of the same 120 subjects.
Original language | English |
---|---|
Title of host publication | Proceedings of the 2005 International Conference on Imaging Science, Systems, and Technology |
Subtitle of host publication | Computer Graphics, CISST'05 |
Pages | 33-39 |
Number of pages | 7 |
Publication status | Published - 1 Dec 2005 |
Event | 2005 International Conference on Imaging Science, Systems, and Technology: Computer Graphics, CISST'05 - Las Vegas, NV, United States Duration: 27 Jun 2005 → 30 Jun 2005 |
Conference
Conference | 2005 International Conference on Imaging Science, Systems, and Technology: Computer Graphics, CISST'05 |
---|---|
Country/Territory | United States |
City | Las Vegas, NV |
Period | 27/06/05 → 30/06/05 |
Keywords
- Biometrics
- Gabor features
- Gabor filters
- Holistic face recognition
- Principal component analysis
ASJC Scopus subject areas
- Computer Graphics and Computer-Aided Design
- Computer Vision and Pattern Recognition