Using Words to Search a Thousand Images: Hierarchical Faceted Metadata in Search Interfaces

Marti Hearst, UC Berkeley SIMS
hearst@sims.berkeley.edu

Seminar on People, Computers, and Design
Stanford University January 17, 2003

Large image collections are rapidly coming online. The most popular image search interfaces are quite simple: users enter keywords, and matching images are shown in a table, ordered by some measure of relevance. These systems can be effective for very specific queries, but do not support browsing and exploratory tasks well. This is true despite the fact that ethnographic studies find that journalists, designers, art directors, and other professionals who use images heavily want to browse images in a flexible manner.

In this talk I will present an interface paradigm called Flamenco which allows users to navigate explicitly along conceptual dimensions that describe the collections' items. The interface makes use of hierarchical faceted metadata and dynamically generated query previews to seamlessly integrate category browsing with keyword searching. I will also present the results of a new usability study, conducted with art history students and fine arts images, that found strong preference results for the faceted category interface over that of the standard approach, suggesting this is a promising approach for image search interfaces.

Dr. Marti Hearst is an associate professor in SIMS, the School of Information Management and Systems at UC Berkeley, with an affiliate appointment in the Computer Science Division. Her primary research interests are user interfaces and visualization for information retrieval, empirical computational linguistics, and text data mining.

She received BA, MS, and PhD degrees in Computer Science from the University of California at Berkeley, and she was a Member of the Research Staff at Xerox PARC from 1994 to 1997. Prof. Hearst is on the editorial boards of ACM Transactions on Information Systems and ACM Transactions on Computer-Human Interaction and was formerly on the boards of Computational Linguistics and IEEE Intelligent Systems. She is the program co-chair of HLT-NAACL '03 and SIGIR '99. She has received an NSF CAREER award, an IBM Faculty Award, an Okawa FoundationFellowship, and two student-initiated Excellence in Teaching awards.

.

View this talk on line at CS547 on Stanford OnLine

Titles and abstracts for all years are available by year and by speaker.

For more information about HCI at Stanford see