CanFind-a semantic image indexing and retrieval system

Abstract

We present CanFind, a semantic image indexing and retrieval system in this paper. To identify the target images of interest in the database in the conceptual level, the presented system makes use of keywords as the input of searching vehicle. The system consists of two subsystems, i.e., semantic indexing and query expansion. In the semantic indexing, the subsystem includes three main building blocks, namely, keyword extraction, keyword expansion, and keyword weighting. The information of WordNet is used to extend existing keywords associated with images. This design intends to overcome the drawbacks in conventional keyword-based image retrieval system. Next, the resulting word set is filtered by a filter to extract common words from the word set and set up the image indexing for the corresponding image. In the query expansion, corpus is used to help users find relative or precise results in the facing dilemma of too few or too many query results for a given query. The designed semantic image indexing and retrieval system is integrated with IWiLL, a web-based language learning platform to further illustrate the value of the designed system.