Back to Search
Start Over
Learning With l¹ Graph for Image Analysis.
- Source :
-
IEEE Transactions on Image Processing . Apr2010, Vol. 19 Issue 4, p858-866. 9p. 2 Diagrams, 9 Charts, 3 Graphs. - Publication Year :
- 2010
-
Abstract
- The graph construction procedure essentially determines the potentials of those graph-oriented learning algorithms for image analysis. In this paper, we propose a process to build the so-called directed l¹-graph, in which the vertices involve all the samples and the in-going edge weights to each vertex describe its l¹-norm driven reconstruction from the remaining samples and the noise. Then, a series of new algorithms for various machine learning tasks, e.g., data clustering, subspace learning, and semisupervised learning, are derived upon the l¹-graphs. Compared with the conventional k-nearest-neighbor graph and ε-ball graph, the l¹-graph possesses the advantages: 1) greater robustness to data noise, 2) automatic sparsity, and 3) adaptive neighborhood for individual datum. Extensive experiments on three real-world datasets show the consistent superiority of l¹-graph over those classic graphs in data clustering, subspace learning, and semi-supervised learning tasks. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 10577149
- Volume :
- 19
- Issue :
- 4
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Image Processing
- Publication Type :
- Academic Journal
- Accession number :
- 48678364
- Full Text :
- https://doi.org/10.1109/TIP.2009.2038764