Skip to Main Content
Integrating multiple features content-based image retrieval can overcome the problems of single feature, but how to combine these features and feature representation methods is important in image retrieval. In this paper an image feature retrieval setting up weight automatically based on particle swarm optimization algorithm is proposed, which could guide the movement direction for particles, and close to ideal solution set quickly. Considering the characteristics of medical image, the contour let transform is used for texture feature extraction. Zernike moments extracts shape feature. The experimental results show that the recall and precision of this proposed approach is better. It can get the best feature combination for medical image retrieval.
Date of Conference: 1-3 Nov. 2010