The Effect of Query Type on Subject Searching Behavior of Image Databases: an Exploratory Study
Efthimis N. Efthimiadis, Raya Fidel · 2000
searching. 1. AIMS The objective of this study is to investigate how different types of queries affect searching behavior in an image retrieval system. Understanding how query types affect search behavior will in turn lead to improved indexing of images. 2. BACKGROUND The explosion of the World Wide Web has facilitated the proliferation of digital image repositories and has exponentially increased the access to collections of digitized images. As a result image management and retrieval has attracted increased attention. In addition, an increasing number of image collections are being digitized and made available for retrieval by end subjects. Early research pointed to the need for textual description i combination with visual resource browsing tools [1][9]. Today, much research is focused on the technical aspects of image indexing and retrieval, using a variety of approaches with algorithms, e.g., [3][7], and AI techniques, e.g., [11]. Some approaches are based on the images themselves (content-based retrieval) and others on the text in images or around images (concept-based retrieval). Despite all these research activities little attention has been paid to the subject side of image retrieval, especially to fundamental Permissmn to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advan-tage and that copras bear this notice and the full citation on the first page 'To copy otherwise, to repubhsh, to post on servers or to redistribute to lists, requires prior specdlc permission and/or a fee.