Technical report
OA Policy
English

Performance Evaluation in Content-Based Image Retrieval: Overview and Proposals

PublisherGenève
Collection
  • Technical report VISION; 99.05
Publication date1999
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 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.

Keywords
  • content-based image retrieval
  • performance evaluation
  • information retrieval
Citation (ISO format)
MULLER, Henning et al. Performance Evaluation in Content-Based Image Retrieval: Overview and Proposals. 1999
Main files (1)
Report
accessLevelPublic
Identifiers
  • PID : unige:48034
639views
1857downloads

Technical informations

Creation03/09/2015 11:34:28 AM
First validation03/09/2015 11:34:28 AM
Update time03/14/2023 11:00:32 PM
Status update03/14/2023 11:00:32 PM
Last indexation10/30/2024 11:27:04 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack