Multi-Feature Indexing for Image Retrieval Based on Hypergraph

Based on the fact that tourism photos on the Internet have a lot of additional information, we proposed a novel tourism image retrieval method based on hypergraph (HMIR). The proposed method utilizes hypergraph to establish the relationship among different types of low-level visual features of images and their additional information (such as shooting locations, user-defined tags, etc.), and the fusion of different features is then performed at the offline indexing stage using random walk and similar image set (SI) replacement. Then Bag of Words method is used for image retrieval at online query stage. During online retrieval stage, we only need to extract local descriptors from queries, and can get semantic-aware retrieval results. Experiments show that compared with several other image retrieval methods based on single feature or multiple feature, the proposed method can improve the performance of image retrieval using different evaluation methods.