A feedforward control idea for CBIR using obvious features

CBIR (Content-Based Image Retrieval), which includes feature selection, feature extraction, similarity measurement and user feedback parts, often uses feedback to improve the retrieval accuracy. But there are two problems of Feedback: 1) improving the retrieval accuracy, but also increasing the user's operation complexity; 2) it is not easy to confirm the weight values of each feature in similarity measurement. In this paper, a feedforward idea from Control Theory was used in CBIR system. The method is to select an obvious feature automatically from multi-features, and then give a higher weight value to the obvious feature in the similarity measurement. Experiment results show that the method presented is efficient in image retrieval based on feedforward idea. © 2009 Copyright SPIE - The International Society for Optical Engineering.