Implementation of multikernel sparse representation on remote sensing image classification

This paper presents a novel multikernel based Sparse representation for the classification of Remotely sensed images. The sparse representation based feature extraction are in a run which is a signal dependent feature extraction and thus more accurate. Multikernel Sparse representation was also had proved to be more accurate and less computationally complex while implemented in other applications like the video object tracking. Affine transform based templates are extracted from the image which has to be trained and the kernel matrix is generated which is used for comparison with the templates extracted from the test images. Kernel Coordinate Descent (KCD) algorithm. The weight values updated using the observation likelihood calculation from the proposed algorithm is used to train the SVM for the image classification in remote sensing images. The template with the highest weight values would be taken as the classified portion of the query image. Matlab based implementation is carried out on the image classification using the Multikernel Sparse Represenation (MKSR) and the results are observed and tabulated.