Relevance feedback of content-based image retrieval using support vector machine

The rapid growth of computer technologies and the advent of the World Wide Web have increased the amount and the complexity of multimedia information. A content-based image retrieval (CBIR) system has been developed as an efficient image retrieval tool, whereby the user can provide their query to the system to allow it to retrieve the user's desired image from the image database. However, the traditional relevance feedback of CBIR has some limitations that will decrease the performance of the CBIR system, such as the imbalance of training-set problem, classification problem, limited information from user problem, and insufficient training-set problem. Therefore, in this study, we proposed an enhanced relevance-feedback method to support the user query based on the representative image selection and weight ranking of the images retrieved. The support vector machine (SVM) has been used to support the learning process to reduce the semantic gap between the user and the CBIR system. From these experiments, the proposed learning method has enabled users to improve their search results based on the performance of CBIR system. In addition, the experiments also proved that by solving the imbalance training set issue, the performance of CBIR could be improved.