Extended performance graphs for cluster retrieval

Author

Huijsmans, D.P. ; Sebe, N.

Author_Institution

Inst. of Adv. Comput. Sci., Leiden Univ., Netherlands

Volume

1

fYear

2001

fDate

2001

Abstract

Performance evaluations in probabilistic information retrieval are often presented as precision-recall or precision-scope graphs avoiding the otherwise dominating effect of the embedding irrelevant fraction. However, precision and recall values as such offer an incomplete overview of the information retrieval system under study: information about system parameters like generality (the embedding of the relevant fraction), random performance, and the effect of varying the scope is missed In this paper two cluster performance graphs are presented In those cases where complete ground truth is available (both cluster size and database size) the cluster precision-recall (Cluster PR) graph and the generality-precision=recall graph are proposed.

Keywords

information retrieval; performance evaluation; visual databases; cluster retrieval; cluster size; complete ground truth; database size; extended performance graphs; performance evaluations; precision recall; precision scope graphs; probabilistic information retrieval; random performance; system parameters; Area measurement; Audio databases; Books; Computer science; Content based retrieval; Image databases; Image retrieval; Information retrieval; NIST; Performance analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on

ISSN

1063-6919

Print_ISBN

0-7695-1272-0

Type

conf

DOI

10.1109/CVPR.2001.990452

Filename

990452