A novel K-RBP dictionary learning algorithm for video image sparse representation

Dictionary learning algorithm is a powerful video image sparse representation method that has attracted much interest in signal processing. The K-SVD algorithm has achieved success in sparse representation feat but suffers from the problems of underutilization of dictionary atoms and calculates SVD excessively for the whole atoms during each iteration procedure. However, the K-RBP (Random Bilateral Projection) dictionary learning algorithm offers a novel dictionary update method which on account of computing the largest singular value and its corresponding singular vector which reduces deviation and complexity, saves the computational space and gives the training vectors a good enough chance to become enough sparsity over the overcomplete dictionary. Simulation results show that when sparsely represent video image frames with the K-RBP dictionary learning algorithm, the efficiency of reconstruction is better than others in the case of image frames based on compressive sensing. Copyright © 2015 Binary Information Press.