Edge Detection for Hyperspectral Images Using the Bhattacharyya Distance

Abstract

In this paper, we proposed a new edge detection algorithm for hyper spectral images using the Bhattacharyya distance. First, the principal component analysis is applied to hyper spectral images and then dominant eigenimages are selected. To compute the Bhattacharyya distance, four block pairs of each pixel are extracted: up-down, left-right, diagonal-left down and diagonal-right-down. From each pair of blocks, we compute the Bhattacharyya distance, which was used as edge information. Experiments show promising results compared to the conventional Sobel filter.