Target testing and the PicHunter Bayesian multimedia retrieval system

Publisher Website
Google Scholar
Abstract
This paper addresses how the effectiveness of a content-based, multimedia information retrieval system can be measured, and how such a system should best use response feedback in performing searches. We propose a simple, quantifiable measure of an image retrieval system's effectiveness, "target testing'', in which effectiveness is measured as the average number of images that a user must examine in searching for a given random target. We describe an initial version of PicHunter, a retrieval system designed to test a novel approach to relevance-feedback. This approach is based on a Bayesian framework that incorporates an explicit model of the user's selection process. PicHunter is intentionally designed to have a minimal, queryless user interface, so that its performance reflects only the performance of the relevance feedback algorithm. The algorithm, however, can easily be incorporated into more traditional, query-based systems. Employing no explicit query, and only a small amount of image processing, PicHunters able to locate randomly selected targets in a database of 4522 images after displaying an average of only 55 groups of 4 images. This is more than 10 times better than random chance. It may be that, with better image processing and some other improvements discussed in this paper, PicHunter can be improved to the point where it is practical on its %own, with only its present, queryless user-interface.

This publication has 16 references indexed in Scilit: