Retrieving Images by Appearance

A system to retrieve images using a description of the image intensity surface is presented. Gaussian derivative lters at several scales are applied to the image and low order 2D di erential invariants are computed. The resulting multi-scale representation is indexed for rapid retrieval. Queries are designed by the users from an example image by selecting appropriate regions. The invariant vectors corresponding to these regions are matched with the database counterparts both in feature and coordinate space. This yields a match score per image. Images are sorted by the match score and displayed. Experiments conducted with over 1500 images of objects embedded in arbitrary backgrounds are described. It is observed that images similar in appearance and whose viewpoint is within small view variations of the query can be retrieved with an average precision1 of 56%.

• Type: Conference
• Year: 1998
• Where: ICCV
• Authors: S. Ravela, R. Manmatha
• Keywords: Computer Vision, Gaussian Derivative Lters, ICCV 1998, Image Intensity Surface, Match Score, Order 2D Di, Small View Variations