2001
@article{MMS2001,
vgclass = {refpap},
vgproject = {cbir,viper},
author = {Henning M\"{u}ller and Wolfgang M\"{u}ller and David McG.\
Squire and St\'{e}phane Marchand-Maillet and Thierry Pun},
title = {Performance Evaluation in Content-Based Image Retrieval: {O}verview and Proposals},
journal = {Pattern Recognition Letters},
volume = {22},
number = {5},
pages = {593--601},
year = {2001},
note = {(special issue on Image/Video Indexing and Retrieval)},
doi = {http://dx.doi.org/10.1016/S0167-8655(00)00118-5},
url1 = {/publications/postscript/2000/MuellerHMuellerWSquireMarchandPun_prl2000.ps.gz},
url2 = {/publications/postscript/2000/MuellerHMuellerWSquireMarchandPun_prl2000.pdf},
abstract = {Evaluation of retrieval performance is a crucial problem
in content-based image retrieval (CBIR). Many different methods for
measuring the performance of a system have been created and used by
researchers. This article discusses the advantages and shortcomings of
the performance measures currently used. Problems such as defining a
common image database for performance comparisons and a means of
getting relevance judgments (or ground truth) for queries are
explained.
The relationship between CBIR and information retrieval (IR) is made
clear, since IR researchers have decades of experience with the
evaluation problem. Many of their solutions can be used for CBIR,
despite the differences between the fields. Several methods used in
text retrieval are explained. Proposals for performance measures and
means of developing a standard test suite for CBIR, similar to that
used in IR at the annual Text REtrieval Conference (TREC), are
presented.},
}