:Image retrieval systems are widespread in areas such as online shopping, etc. Usually images are retrieved according to the annotated texts. This text image retrieval needs a lot of load of time and effort to annotate the images. As an effective retrieval system, Kansei image retrieval system is proposed. By Kansei retrieval system we can retrieve images based only on adjective but not on noun. This fact leads limited use of Kansei retrieval systems in online shopping area. One of our main aims of this paper is to propose a noun and adjective based image retrieval system. In order to propose noun based image retrieval method, we apply MTS method, since MTS method is a useful pattern information processing method by the use of Mahalanobis distance. We construct image retrieval system for apparel products, and investigate accuracy of noun retrieval and fitness of noun and adjective based retrieved image.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.