A re-examination of relevance: toward a dynamic, situational definition
Information Processing and Management: an International Journal
International Journal of Computer Vision
Texture Features for Browsing and Retrieval of Image Data
IEEE Transactions on Pattern Analysis and Machine Intelligence
Spectral covariance and fuzzy regions for image indexing
Machine Vision and Applications
Introduction to Modern Information Retrieval
Introduction to Modern Information Retrieval
Hierarchical partitions for content image retrieval from large-scale database
MLDM'05 Proceedings of the 4th international conference on Machine Learning and Data Mining in Pattern Recognition
| Hi-index | 0.00 |
Performance evaluation is an often neglected topic in content based image retrieval research. Commonly used evaluation measures for effectiveness assessment are reviewed and their shortcomings are discussed. A new evaluation measure is proposed which overcomes some of the shortcomings of existing evaluation measures. The presented performance measure is especially suited for rank based retrieval methods. The measure is obtained fully automatic and can be exploit to investigate different criteria of effectiveness in detail. For better comparison of performance differences, the measure provides a confidence and credibility measure, too. Experiments were carried out to study the properties of the evaluation method.