Contemporary Content-based Image Retrieval (CBIR) systems are often limited in their ability to capture user perception. Additionally, a significant overhead is incurred in database search and image downloadtime by the relevance feedback approaches in client-server environments. We present a novel methodology for understanding user perception through a set of interactive tools. Our system uses a query by example methodology and uses color, texture and shape parameters for perceptual matching. It provides an object-level view of the query image through image segmentation. We supplement the traditional relevance feedback techniques on the searched results with intra-query learning where the user perception is learnt through feedback on a set of images automatically modified from the query image itself, thus, alleviating the overheads of database search and image download. In addition, we allow the user to explicitly redefine the query point by manually modifying the query image. We demonstrate the feasibility andadvantages of the approach with examples.
By: Gaurav Aggarwal, Pradeep Dubey, Sugata Ghosal, Ashutosh Kulshreshtha, Abhinanda Sarkar
Published in: RI99090 in 1999
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .