A novel semi-supervised kernel feature extraction algorithm to combine an efficient metric learning method, i.e. relevant component analysis (RCA), and kernel trick is presented for hyperspectral imagery land-cover classification. This method obtains projection of the input data by learning an optimal nonlinear transformation via a chunklet constraints-based FDA criterion, and called chunklet-based kernel relevant component analysis (CKRCA). The proposed method is appealing as it constructs the kernel very intuitively for the RCA method and does not require any labeled information. The effectiveness of the proposed CKRCA is successfully illustrated in hyperspectral remote sensing image classification. Experimental results demonstrate that the proposed method can greatly improve the classification accuracy compared with traditional linear and conventional kernel-based methods.
Publié le : 2017-05-12
Classification:  other areas of Computing and Informatics,  Feature extraction, hyperspectral remote sensing image, chunklet constraints, kernel method
@article{cai2017_1_205,
     author = {Haishi Zhao; College of Earth Science, Jilin University, Changchun and Laijun Lu; College of Earth Science, Jilin University, Changchun and Chen Yang; College of Earth Science, Jilin University, Changchun and Renchun Guan; College of Computer Science and Technology, Jilin University, Changchun},
     title = {Kernel Feature Extraction for Hyperspectral Image Classification Using Chunklet Constraints},
     journal = {Computing and Informatics},
     volume = {35},
     number = {4},
     year = {2017},
     language = {en},
     url = {http://dml.mathdoc.fr/item/cai2017_1_205}
}
Haishi Zhao; College of Earth Science, Jilin University, Changchun; Laijun Lu; College of Earth Science, Jilin University, Changchun; Chen Yang; College of Earth Science, Jilin University, Changchun; Renchun Guan; College of Computer Science and Technology, Jilin University, Changchun. Kernel Feature Extraction for Hyperspectral Image Classification Using Chunklet Constraints. Computing and Informatics, Tome 35 (2017) no. 4, . http://gdmltest.u-ga.fr/item/cai2017_1_205/