Analysis of user need in image archives

Abstract

This paper describes a project in which an analysis was undertaken of user queries addressed to seven libraries which manage archives of widely varying still and moving image material. The sampling procedure is described, in which queries obtained from each library were broadly categorised by image content, identification and accessibility. Attention is focused on the image content requests, for which a categorisation based on facet analysis is developed. The analytical tool which is used for this purpose is based on a schema already well established for the analysis of levels of meaning in images. The project demonstrates the possibility of formulating a general categorisation of requests which seek widely different still and moving image material. The paper concludes with observations on the potential value of embedding such a schema within the user interface of unmediated-query visual information retrieval systems.

The CLEF Cross Language Image Retrieval Track (ImageCLEF) 2004

“…However, in addition to using St. Andrews query logs, we also used subject areas supplied by staff from St. Andrews' library. Topic refinement is based on the query categorisation scheme suggested by Armitage et al [1] for picture archives and designed to test a range of different CL and image search parameters. Topics have been translated into the previous languages, plus Japanese, Danish, Russian, Finnish, Swedish and Arabic.…”

“…Images can then be retrieved using standard IR methods based on textual queries. However, retrieval from an image collection offers distinct characteristics from one in which the document to be retrieved is natural language text [1] [10]. For example, the way in which a query is formulated, the method used for retrieval (e.g.…”

Beyond Nouns: Exploiting Prepositions and Comparative Adjectives for Learning Visual Classifiers

“…For example, since cars are typically found on streets, it is difficult to resolve the correspondence using co-occurrence relationships alone. While such confusion is not a serious impediment for image annotation, it is a problem if localization is a goal 1 .…”

A study on the relevance criteria for medical images

“…Researchers such as Armitage and Enser (1997), Markkula and Sormunen (2000), Greisdorf (2002), Cunningham and Masoodian (2006) and Tsai (2007) have investigated the needs and information seeking behaviour of users searching for images. However such studies have not addressed search of images in medicine.…”