Abstract
Image retrieval plays a major role in an integrated healthcare environment for various purposes, such as computer-aided diagnosis, medical education, Tele-surgeries, evidence-based medicine, and many more. In the retrieval system, two kinds of approaches are mainly followed: Text-Based Image Retrieval (TBIR) and Content-Based Image Retrieval (CBIR). The former approach requires lot of human effort and time, also subject to human perception. The latter approach pays greater attention to global and local information, such as the color, shape, region, and texture of an image. The major drawback of CBIR is its inability to distinguish the characteristics of heterogeneous medical images. Considering the limitations of both approaches, an integrated framework is proposed, based on the distinct characteristics of TBIR and CBIR. In both approaches, the related feature descriptors of images and terms of documents are extracted. In order to reduce the irrelevant features in CBIR, a modified ant colony optimization with a relevance feedback mechanism is incorporated. In this proposed framework, the performance of CBIR, TBIR, and their fusion (combination of TBIR and CBIR) is analyzed and the precision of each approach is 78.8%, 85.9%, and 94.8%, respectively.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Intelligent Data Analysis for Biomedical Applications
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
