A novel image retrieval model
JunWei Han, Lei Guo, YongSheng Bao · 2003
Image retrieval is the important to researchers in many domains. Traditional text-based query methods use caption and keywords to annotate and retrieval image databases, which often consumes a mass of human labor. Feature vector based retrieval methods only can provide the query by example, and cannot provide retrieval on the semantic level. In this paper, we propose a novel image retrieval model that combines good qualities of those two methods mentioned above. It utilizes the image low-level features and the user relevance feedback mechanism to classify images and acquire high-level semantic information. Furthermore, the image classification and the semantic information are not fixed, which can be changed by the user according to his preference. Experiments show that our scheme can achieve high efficiency.