Support vector machine with adaptive composite kernel for hyperspectral image classification

Wei Li; Qian Du

doi:10.1117/12.2178012

Translator Disclaimer

21 May 2015 Support vector machine with adaptive composite kernel for hyperspectral image classification

Wei Li, Qian Du

Author Affiliations +

Proceedings Volume 9501, Satellite Data Compression, Communications, and Processing XI; 95010O (2015) https://doi.org/10.1117/12.2178012
Event: SPIE Sensing Technology + Applications, 2015, Baltimore, Maryland, United States

Abstract

With the improvement of spatial resolution of hyperspectral imagery, it is more reasonable to include spatial information in classification. The resulting spectral-spatial classification outperforms the traditional hyperspectral image classification with spectral information only. Among many spectral-spatial classifiers, support vector machine with composite kernel (SVM-CK) can provide superior performance, with one kernel for spectral information and the other for spatial information. In the original SVM-CK, the spatial information is retrieved by spatial averaging of pixels in a local neighborhood, and used in classifying the central pixel. Obviously, not all the pixels in such a local neighborhood may belong to the same class. Thus, we investigate the performance of Gaussian lowpass filter and an adaptive filter with weights being assigned based on the similarity to the central pixel. The adaptive filter can significantly improve classification accuracy while the Gaussian lowpass filter is less time-consuming and less sensitive to the window size.

Citation Download Citation

Wei Li and Qian Du "Support vector machine with adaptive composite kernel for hyperspectral image classification", Proc. SPIE 9501, Satellite Data Compression, Communications, and Processing XI, 95010O (21 May 2015); https://doi.org/10.1117/12.2178012

ACCESS THE FULL ARTICLE