Design and implementation of web-based systems for image segmentation and CBIR

This paper is focused on the design and development of an architecture that is able to provide remote segmentation service to various kinds of images or applications. The system exploits the functionalities offered by the already existing desktop application Isocontour by extending its capabilities toward a client-server environment. In order to achieve this goal, the original Isocontour code has been decomposed to independent modules for processing, storing, and representing purposes. By using the created server components, a web application has been developed to demonstrate how to make the fuzzy image-segmentation service highly available through the Internet. Furthermore, by exploiting the same architecture seen for the Isocontour algorithm, a remote content-based retrieval service for image databases was implemented in order to show the adaptability of this web-based system. Performance evaluation in terms of processing times with different image sizes has been performed in order to compare the web-based solution with the stand-alone one and to prove the reliability of the proposed system.