Abstract | ||
---|---|---|
In this paper we discuss algorithmically efficient methods of multidimensional patter recognition in kernel tensor subspaces. The kernel principal component analysis, which originally operates only on vector data, is joined with the tensor chordal kernel which opens a way of direct usage of the multidimensional signals, such as color video streams, seismic signals or hyper-spectral images. We address the problem of efficient implementation of the eigendecomposition problem which is a core algorithm for both methods. For this the fixed point algorithm is employed. We show usefulness of this approach on the problem of visual pattern recognition and show speed-up ratio when using the proposed implementation. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-40973-3_54 | DATA MINING AND BIG DATA, DMBD 2016 |
Keywords | Field | DocType |
Kernel PCA, Chordal kernel, Tensor, Subspace classification | Kernel (linear algebra),Tensor,Pattern recognition,Computer science,Chordal graph,Fixed point algorithm,Hyperspectral imaging,Linear subspace,Kernel principal component analysis,Eigendecomposition of a matrix,Artificial intelligence | Conference |
Volume | ISSN | Citations |
9714 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Boguslaw Cyganek | 1 | 145 | 24.53 |
Michał Woźniak | 2 | 213 | 24.64 |