An Immune Clone Particle Swarm Optimization Algorithm for Sparse Representation of Hyperspectral Images

The sparse representation of hyperspectral images can reduce the amount of data and facilitate image classification and interpretation processing. An immune clone particle swarm optimization algorithm (ICPSO) to achieve sparse representation of hyperspectral images is proposed in this paper. The main idea of the algorithm is to use the evolutionary process of particle swarm to simulate the atomic matching process of the orthogonal chasing algorithm to improve the diversity and efficiency of atom selection. Further, according to the clonal selection theory of biological immunology, immune cloning, cloning mutation and cloning selection operators are used to expand the local search range, fully maintain the diversity of the population, improve the convergence speed and avoid the premature convergence. Sparse representation experiments are carried out on hyperspectral images using proposed ICPSO to verify the performance of the algorithm. Compared with the orthogonal matching pursuit algorithm, the proposed algorithm can improve the reconstruction accuracy as well as the computing efficiency.