TY  - JOUR
ID  - MMS2000d
T1  - Performance Evaluation in Content-Based Image Retrieval: Overview and Proposals
A1  - Müller, Henning
A1  - Müller, Wolfgang
A1  - Squire, David McG.
A1  - Marchand-Maillet, Stéphane
A1  - Pun, Thierry
ED  - Bunke, Horst
ED  - Jiang, X.
JA  - Pattern Recognition Letters
Y1  - 2001
VL  - 22
IS  - 5
SP  - 593
EP  - 601
N1  - Special Issue on Image and Video Indexing
KW  - Benchmarking
KW  - image retrieval
KW  - information retrieval evaluation
KW  - Medical image analysis and retrieval
KW  - performance evaluation
N2  - 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.
M1  - vgproject={viper}
M1  - 
vgclass={refpap}
ER  -