A Graph Community and Bag of Categorized Visual Words Based Image Retrieval

Abstract

Abstract. We propose a novel method for organizing image dataset with tags in which each image is regarded as a node of a complex network and the semantic information of the dataset can be grouped with community detection algorithm. The retrieval process are divided into two phases to improve accuracy by searching in a smaller sub-dataset. In the first phase, tags of a query image are taken as the priority matter to select target communities; in the second one, content based image retrieval is performed within the target communities. Bag of categorized visual words model is proposed as image content representation to improve description ability for objects compared with bag of visual words. Besides we also try to implement bag of visual words with SOM classifier.