Hyperspectral image classification by combining local binary pattern and joint sparse representation

This paper proposes a new hyperspectral classification method that combines the joint sparse representation classifier (JSRC) and local binary pattern (LBP) (JSR-LBP). The proposed method uses a statistical histogram of the LBP feature spectrum as a feature vector for classification and recognition. Using the LBP method let us extract the local texture feature of an image more accurately and effectively because of the forceful robustness to light. The proposed method JSR-LBP mainly includes the following steps: First, the JSRC is used to obtain the representation residuals of different pixels. Then, the LBP value is calculated for every pixel in the whole image to generate the LBP histogram; the LBP histogram of the test sample can be obtained from a series of binary codes that are generated using statistics. Next, the Bhattacharyya coefficient is employed to measure the similarity between the test and training samples unlike the traditional classifiers as k-nearest neighbor that usually employ the Euclidean distance as similarity metric, and a regularization parameter λ is then introduced to achieve the balance between the JSRC and LBP. Finally, the test pixel's label is determined by applying the final residual. Experimental results performed on three real hyperspectral images data demonstrate the outstanding performance of the proposed approach compared to other broader classifiers.