Abstract
A system for automatic human face detection and recognition is presented. The procedure consists of five steps: (1) the Haar wavelet transform, (2) facial edge detection, (3) symmetry axis detection, (4) face detection and (5) face recognition. Step 1 decomposes an input image, reducing image redundancy. Step 2 excludes non-facial areas using edge information, whereas Step 3 narrows down face areas further using gradient orientation. Step 4 restricts face-like areas by template matching. Finally, Step 5 determines the best face location in the face-like areas and identifies the face based on principal component analysis (PCA). The system shows a remarkably robust performance under non-uniform lighting conditions. © 1999 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved. Keywords: Wavelet transform; Edge detection; Symmetry detection; Face detection; Face recognition; Template matching; Correlation; Principal component analysis; K-L expansion.
| Original language | English |
|---|---|
| Pages (from-to) | 1707-1718 |
| Journal | Pattern Recognition |
| Volume | 32 |
| Issue number | 10 |
| DOIs | |
| Publication status | Published - Oct 1999 |
| Externally published | Yes |
Research Keywords
- Correlation
- Edge detection
- Face detection
- Face recognition
- K-L expansion
- Principal component analysis
- Symmetry detection
- Template matching
- Wavelet transform