From Textual to Visual Image Searching: User Experience of Advanced Image Search Tool

Abstract

This paper reports findings from a study focusing on user experience of image search tool utilizing content-based image retrieval methods. Previous studies have indicated challenges in textual image search especially in the historical domain. As a part of the project, a prototype tool was created for searching digitized historical images based on their visual contents to provide support for user needs identified in earlier studies. The tool was tested by 15 participants who evaluated their user experience with User Experience Scale and by verbal feedback. Our results indicate that participants derived benefits from the search capabilities provided by the tool, which went beyond relying on textual image descriptions. However, problems occurred, for example, in evaluating the search results and in user skills. Results also emphasize the value of intellectually produced metadata for image searching and use. Therefore, future developments should focus on creating hybrid systems supporting both textual and visual image searching.