Bilateral Kernel Extraction from PCA for Classification of Hyperspectral Images

The improved spatial and spectral resolution in the advanced Hyperspectral (HS) sensors results in images with rich information per pixel. Hence, the development of efficient spatial-spectral feature extraction (FE) techniques is very crucial for a proper characterization of the objects on ground. In this paper, an attempt has been made to develop a simple, yet effective spatial-spectral FE algorithm. In the proposed approach, the following steps are performed. First, Principal Component Analysis (PCA) was applied on the original hyperspectral image (HSI) and the most significant principal component was extracted. Then, the Bilateral Filter (BF), which acts as an edge-preserving filter, was applied on the selected principal component to extract kernel for each pixel in HSI. The extracted kernel bank is then applied on the original HSI. As in general, the principal component image is edge informative, and the BF is an edge-preserving filter; therefore, the extracted kernel bank can be applied on the original HSI to extract spatial-spectral features. Finally, with the help of these features, the performance of Support Vector Machine (SVM) classifier is evaluated. The proposed approach is validated on three popular hyperspectral data sets, namely, Indian Pines, Pavia University, and Botswana. The experimental results reveal that learning the edge information from a reference image (in the present context PCA) is quite essential, rather than applying the edge-preserving filters directly on the HSI. Theoretically, this holds true, as a unique edge (ground) information exists for an HSI, while in reality, the edges have variations due to variation in reflectance over bands.