Abstract
In this paper, new improvements for the linear discrimination technique are proposed. These improvements include effective solutions for the small sample size problem, the selection of appropriate principal component and more accurate within-class scatter estimation for the Fisher criterion. The effectiveness of our approach is proved by experimental results on the Yale face database.
| Original language | English |
|---|---|
| Pages (from-to) | 2695-2701 |
| Number of pages | 7 |
| Journal | Pattern Recognition Letters |
| Volume | 24 |
| Issue number | 15 |
| DOIs | |
| Publication status | Published - 1 Jan 2003 |
Keywords
- Face recognition
- Linear discrimination
- Principal component selection
- Small sample size problem
- Within-class scatter estimation
ASJC Scopus subject areas
- Software
- Signal Processing
- Computer Vision and Pattern Recognition
- Artificial Intelligence
Fingerprint
Dive into the research topics of 'Improvements on the linear discrimination technique with application to face recognition'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver