Acta Photonica Sinica, Volume. 43, Issue 6, 630002(2014)
Manifold based Semi supervised Feature Selection for Hyperspectral Data
The traditional Feature Selection methods of hyperspectral data include supervised and unsupervised modes, is not efficient for the real processing system in which abundant unlabeled and few labeled data coexist. Additionally, most of existing feature selection methods ignore that real data has a manifold structure which embedded into the high dimensional space. In order to solve these problems, a Manifold based Semisupervised Feature Selection (MSFS) algorithm was proposed. Considering the prior information of labeled data with the local and nonlocal invariance of the whole data, the discriminate structure is optimized through simultaneously maximizing betweenclass and minimizing withinclass variances. Meanwhile, the manifold structure is exploited from constructing local and nonlocal graphs for the whole data. Then, the efficient features is selected by defining an appropriate evaluation criterion. Finally, through performing the classification experiment on the selected features of real hyperspectral data, it demonstated that our method is able to retain the main structure of data after dimensionality reduction well.
Get Citation
Copy Citation Text
WEI Feng, HE Mingyi, SHEN Zhiming, LI Xu. Manifold based Semi supervised Feature Selection for Hyperspectral Data[J]. Acta Photonica Sinica, 2014, 43(6): 630002
Received: Jan. 23, 2014
Accepted: --
Published Online: Aug. 18, 2014
The Author Email: Feng WEI (weifengg@163.com)