A Trademark Retrieval Method Based on Support Vector Machines Self-Learning

Relevance feedback is a good method for semantic gap in image retrieval. In this paper we propose a method which uses support vector machines for conducting effective relevance feedback for trademark retrieval. The algorithm takes the test results to adjust the already trained support vector machines. We select the Tamura textures features which consistent with human vision perception and the low-level feature of image to train support vector machines. Experimental results show that it achieves significantly higher search accuracy after just three or four rounds of relevance feedback.