Medical Image Registration Based on JS Measure and Niche Chaotic Mutation Quantum-Behaved Particle Swarm Optimization

To the problem of the premature convergence and lower searching precision of the standard particle swarm optimization (PSO), this paper provides niche chaotic mutation quantum-behaved particle swarm optimization (NCQPSO) algorithm for image elastic registration, through maximizing the value of JS measure to achieve. In this algorithm, niche methods and eliminating strategy are introduced to improve the global optimizing ability. Furthermore, shrinking chaotic mutation, which behaves well in refined local traversal searching, is introduced to improve the precision. The experimental results show that the NCQPSO algorithm as an optimization strategy is a better solution to the registration of global optimization problems, with good accuracy and robustness.