1997
@techreport{SqP1997b,
vgclass = {report},
vgproject = {viper,cbir},
author = {David McG. Squire and Thierry Pun},
title = {Using human partitionings of an image set to learn a
similarity-based distance measure},
number = {97.06},
institution = {Computer Vision Group, Computing Centre, University
of Geneva},
address = {rue G\'{e}n\'{e}ral Dufour, 24, CH-1211 Gen\`{e}ve,
Switzerland},
month = {November},
year = {1997},
url = {/publications/postscript/1997/VGTR97.06_SquirePun.pdf},
url1 = {/publications/postscript/1997/VGTR97.06_SquirePun.ps.gz},
abstract = {In this paper our goal is to employ human judgments of
image similarity to improve the organization of an image database for
content-based retrieval. We first derive a statistic, $\kappa_B$ for
measuring the agreement between two partitionings of an image set into
unlabeled subsets. This measure can be used both to measure the degree
of agreement between pairs of human subjects, and also between human
and machine partitionings of an image set. This provides a rigorous
means of selecting between competing image database organization
systems, and assessing how close the performance of such systems is to
that which might be expected from a database organization done by hand.
We then use the results of experiments in which human subjects are
asked to partition a set of images into unlabeled subsets to define a
similarity measure for pairs of images based on the frequency with
which they were judged to be similar. We show that, when this measure
is used to partition an image set using a clustering technique, the
resultant clustering agrees better with those produced by human
subjects than any of the feature space-based techniques investigated.
Finally, we investigate the use of machine learning techniques to
discover a mapping from a numerical feature space to this perceptual
similarity space. Such a mapping would allow the ground truth knowledge
abstracted from the human judgments to be generalized to unseen
images.},
}