Image Retrieval Relevance Feedback Algorithm Based on Particle Swarm Optimization-Shuffled Frog Leaping Algorithm

Aim at the semantic gap between visual low level features and high level semantics, this paper proposed a method that imported particle swarm optimization-shuffled frog leaping algorithm into the relevance feedback on the content-based image retrieval. Feedback process is optimized by using particle swarm optimization-shuffled frog leaping algorithm, on the one hand enhance the retrieval ability, makes retrieval can jump out of the sub-optimal, on the other hand through the optimization iteration of the particles that users evaluate the retrieved images, makes the computer understand the needs of users. Through the simulation experiments showing that the proposed method can effectively improve the precision of image retrieval.