An effective relevance feedback algorithm for image retrieval

Relevance feedback (RF) is an effective method for content-based image retrieval (CBIR), and it is also a feasible step to shorten the semantic gap between low-level visual feature and high-level perception. In this paper, a SVM-based RF algorithm is proposed to improve performance of image retrieval. In classifier training, a sample expanding scheme is adopted to balance the proportion of positive samples and negative samples. And then, a fusion scheme for multiple classifiers based on adaptive weighting is proposed to vote the final query results. The experimental results on Corel image dataset show the effectiveness of the proposed algorithm.