Sketch retrieval and relevance feedback with biased SVM classification

This paper proposes an effective approach for content-based sketch retrieval. It addresses three characteristics as follows. Firstly, both structural relations and global shape descriptors are combined to represent sketch content. Secondly, feature weighting and combination are performed to obtain a reasonable mechanism for similarity calculation. Finally, relevance feedback based on biased SVM (BSVM) algorithm is employed to capture user’s query interests online and thus improve retrieval performance. Experiments prove the effectiveness of our proposed method in sketch retrieval.