K. Rodden, W. Basalaj, D. Sinclair, and K. Wood
A similarity metric based on the low-level content of images can be used to create a visualisation in which visually similar images are displayed close to each other. We are carrying out a series of experiments to evaluate the usefulness of this type of visualisation as an image browsing aid. The experiment described here considered the task of finding photographs matching a general textual description. Preliminary results indicate that people are faster when the images are displayed in a similarity-based visualisation than when they are arranged randomly.
Short paper and poster, presented at the ACM Conference on Research and Development in Information Retrieval (ACM SIGIR'99), Berkeley, August 1999.
PDF format (1 MB)