Back to Search
Start Over
Feature extraction using two-dimensional maximum embedding difference
- Source :
- Information Sciences. 274:55-69
- Publication Year :
- 2014
- Publisher :
- Elsevier BV, 2014.
-
Abstract
- In this paper we propose a novel method combining graph embedding and difference criterion techniques for image feature extraction, namely two-dimensional maximum embedding difference (2DMED). This method directly extracts the optimal projective vectors from 2D image matrices by simultaneously considering characteristic that is the intraclass compactness graph, the margin graph and inter-class separability graph, respectively. In this method, it is not necessary to convert the image matrix into high-dimensional image vector so that much computational time would be saved. In addition, the proposed method preserves the manifold reconstruction relationships in the low-dimensional subspace. Experimental results on the ORL, Yale face and USPS database show the effectiveness of the proposed method.
- Subjects :
- Information Systems and Management
Graph embedding
business.industry
Feature extraction
Pattern recognition
Strength of a graph
Computer Science Applications
Theoretical Computer Science
Graph energy
Graph bandwidth
Artificial Intelligence
Control and Systems Engineering
Computer Science::Computer Vision and Pattern Recognition
Graph (abstract data type)
Embedding
Adjacency matrix
Artificial intelligence
business
Software
Mathematics
Subjects
Details
- ISSN :
- 00200255
- Volume :
- 274
- Database :
- OpenAIRE
- Journal :
- Information Sciences
- Accession number :
- edsair.doi...........f5c60aa0db3203c33a88f3b7aeb9f61c