Texture feature extraction of hyper-spectral image with three-dimensional gray-level co-occurrence

To extract useful information of hyper-spectral images effectively, a kind of texture feature extraction method using three-dimensional gray-level co-occurrence matrix (3d glcm) is proposed in this paper. the method extracts the texture features of hyper-spectral image as a pseudo data cube that combines the two-dimensional space data with one-dimensional spectrum data, instead of each band computed alone. moreover, the parameters related to building the 3d glcm are all optimized. to obtain the features both in spectral space and spatial space, the moving directions of texture window are extended to the spectral space, namely that four directions in two-dimensional (2d) image space are expanded to thirteen ones in three-dimensional (3d) space. then, the jeffreys-matusita (jm) distance based on the class separable criterion is employed to select the most suitable window size for each object. finally, the multi-scale texture features are used for classification. the experiments also show that, compared with the traditional methods, the feature extraction method is more effective in describing objects and has better classification accuracy. ©, 2015, binary information press