Copyright 1998 Society of Photo-Optical Instrumentation Engineers. This paper was (will be) published in SPIE Proceedings and is made available as an electronic reprint [preprint] with permission of SPIE. Single print or electronic copies for personal use only are allowed. Systematic or multiple reproduction, distribution to multiple locations through an electronic listserver or other electronic means, duplication of any material in this paper for a fee or for commericial purposes, or modification of the content of the pater are all prohibited. By choosing to view or print this document, you agree to all the provisions of the copyright law protecting it.
In this paper, we study how human observers judge image similarity. To do so, we have conducted two psychophysical scaling experiments and have compared the results to two algorithmic image similarity metrics. For these experiments, we selected a set of 97 digitized photographic images which represent a range of semantic categories, viewing distances and colors. We then used the two perceptual and the two algorithmic methods to measure the similarith of each image to every other image in the data set, producing four similarity matrices. These matrices were analysed using multidimensional scaling techniques to gain insight into the dimensions human observers use for judging image similarity, and how these dimensions differ from the results of algorighmic methods. This paper also describes and validates a new technique for collecting similarity judgments which can provide meaningful results with a factor of four fewer judgments, as compared with the paired comparisons method.
By: Bernice E. Rogowitz, Thomas Frese, John R. Smith, Charles A. Bouman, Edward Kalin
Published in: SPIE Proceedings, volume , (no ), pages 576-90 in 1998
Please obtain a copy of this paper from your local library. IBM cannot distribute this paper externally.
Questions about this service can be mailed to reports@us.ibm.com .