Abstract
This paper develops a "Non-locality" Preserving Projection (NLPP) technique for feature extraction. In contrast to the existing Locality Preserving Projection (LPP), a technique based on the characterization of the local scatter, NLPP is a method based on the characterization of the non-local scatter. Intuitively, NLPP should be more effective than LPP when the non-local information plan a dominant role in discrimination. NLPP is tested using the PolyU palmprint database and the experimental results show that NLPP outperforms PCA, LDA and LPP.
Original language | English |
---|---|
Title of host publication | 9th International Conference on Control, Automation, Robotics and Vision, 2006, ICARCV '06 |
DOIs | |
Publication status | Published - 1 Dec 2006 |
Event | 9th International Conference on Control, Automation, Robotics and Vision, 2006, ICARCV '06 - Singapore, Singapore Duration: 5 Dec 2006 → 8 Dec 2006 |
Conference
Conference | 9th International Conference on Control, Automation, Robotics and Vision, 2006, ICARCV '06 |
---|---|
Country/Territory | Singapore |
City | Singapore |
Period | 5/12/06 → 8/12/06 |
Keywords
- Biometrics
- Feature extraction
- Manifold learning
- Palmprint recognition
- Subspace learning
ASJC Scopus subject areas
- Computer Science Applications
- Computer Vision and Pattern Recognition
- Control and Systems Engineering