Abstract | ||
---|---|---|
Isomap is a classical manifold learning approach that preserves geodesic distance of nonlinear data sets. One of the main drawbacks of this method is that it is susceptible to leaking, where a shortcut appears between normally separated portions of a manifold. We propose an adaptive graph construction approach that is based upon the sparsity property of the l(1) norm. The l(1) enhanced graph construction method replaces k-nearest neighbors in the classical approach. The proposed algorithm is first tested on the data sets from the UCI data base repository which showed that the proposed approach performs better than the classical approach. Next, the proposed approach is applied to two image data sets and achieved improved performances over standard Isomap. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1117/12.2082646 | IMAGE PROCESSING: ALGORITHMS AND SYSTEMS XIII |
Field | DocType | Volume |
Data set,Nonlinear system,Pattern recognition,Sparse approximation,Manifold alignment,Artificial intelligence,Nonlinear dimensionality reduction,Geodesic,Mathematics,Manifold,Isomap | Conference | 9399 |
ISSN | Citations | PageRank |
0277-786X | 2 | 0.39 |
References | Authors | |
5 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Loc Tran | 1 | 62 | 6.46 |
Zezhong Zheng | 2 | 29 | 12.43 |
Guoqing Zhou | 3 | 25 | 15.98 |
jiang li | 4 | 23 | 9.88 |