A study on Content-based Image Retrieval System Using Relevance Feedback

As digital images quickly increase in number, adopting effective content-based image retrieval (CBIR) algorithm to retrieval the desired images is essential nowadays with the presence of a huge amount of digital images, the present paper introduces an accurate and rapid mode for content based image retrieval process. The algorithm is composed of two major phases, namely features extraction and relevance feedback. In the feature extraction phase, it uses the improved DCD algorithm to extract color feature and LBP algorithm to extract the texture feature, with the SVM algorithm adopted in the relevance feedback phase. Experimental results show that the proposed method has higher retrieval accuracy than other conventional ones.