Increasing demands for image retrieval in field such as health informatics, biometrics, and crime prevention has forced developers to explore ways to manage and retrieve images more efficiently. An automated way to retrieve images based on the content or features of the images itself is provided by CBIR. Shape is one of key visual features used by human for distinguishing visual data along with other features of color and texture. Therefore, this work investigates one of the shape representation method shape context which helps in efficient CBIR.The main aim of this research is to look for and develop promising shape descriptor(s) which was found to be Shape Context for image retrieval and also to improve efficiency. The Shape context descriptor is contour based which focuses on irregular shapes. The time consuming step of shape context matching is reduced in this work up to approx. 48% on an average. The proposed work reduces the computational complexity maintaining its overall accuracy.
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.