Automatic semantic annotation of images based on Web data

Image annotation is a promising approach to bridging the semantic gap between low-level features and high-level concepts, and it can avoid the heavy manual labor. Most existing automatic image annotation approaches are based on supervised learning. They often encounter several problems, such as insufficiency of training data, lack of ability in dealing with new concept, and a limited number of semantic concepts. Web images are massive, rich information, customized etc. Therefore, Web data is a potential repository to provide a sufficient source for semantic annotation. In this paper, we proposed a novel image annotation method based on Web data, which aims to utilize Web data to perform automatic image annotation. Web data, collected from several image search engine, are first preprocessed, clustered and mined to construct a concept clustering model. And then candidate annotation terms are extracted through the model for query image. Afterwards, a rank algorithm is designed to filter out noise terms. Finally, an update phase is implemented to improve the whole method. Evaluations on benchmark image datasets have indicated the effectiveness of our proposal.