Abstract
This paper develops a method called locally principal component analysis (LPCA) for data representation. LPCA is a linear and unsupervised subspace-learning technique, which focuses on the data points within local neighborhoods and seeks to discover the local structure of data. This local structure may contain useful information for discrimination. LPCA is tested and evaluated using the AT&T face database. The experimental results show that LPCA is effective for dimension reduction and more powerful than PCA for face recognition.
Original language | English |
---|---|
Pages (from-to) | 1697-1701 |
Number of pages | 5 |
Journal | Neurocomputing |
Volume | 69 |
Issue number | 13-15 |
DOIs | |
Publication status | Published - 1 Aug 2006 |
Keywords
- Dimensionality reduction
- Face recognition
- Feature extraction
- Locality-based learning
- Principal component analysis (PCA)
ASJC Scopus subject areas
- Computer Science Applications
- Cognitive Neuroscience
- Artificial Intelligence