Towards automatic detection of CBIRs configuration

Authors:
Christian Vilsmaier;Rolf Karp;Mario Döller;Harald Kosch;Lionel Brunie
Affiliations:
INSA de Lyon, LIRIS, Villeurbanne Cedex, France;Distributed and Multimedia Information Sytems, University of Passau, Passau, Germany;Distributed and Multimedia Information Sytems, University of Passau, Passau, Germany;Distributed and Multimedia Information Sytems, University of Passau, Passau, Germany;INSA de Lyon, LIRIS, Villeurbanne Cedex, France
Venue:
MMM'12 Proceedings of the 18th international conference on Advances in Multimedia Modeling
Year:
2012

Citing 7
Cited 0

Content-Based Image Retrieval at the End of the Early Years

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Method for Evaluating the Performance of Content-Based Image Retrieval Systems Based on Subjectively Determined Similarity between Images

CIVR '02 Proceedings of the International Conference on Image and Video Retrieval
Evaluation of content-based image descriptors by statistical methods

Multimedia Tools and Applications
Image retrieval: Ideas, influences, and trends of the new age

ACM Computing Surveys (CSUR)
Features for image retrieval: an experimental comparison

Information Retrieval
Building self-organized image retrieval network

Proceedings of the 2008 ACM workshop on Large-Scale distributed systems for information retrieval
Lire: lucene image retrieval: an extensible java CBIR library

MM '08 Proceedings of the 16th ACM international conference on Multimedia

Quantified Score

Hi-index	0.00

Visualization

Abstract

Many Content Based Image Retrieval system s (CBIRs) have been invented in the last decade. The general mechanism of the search process is very similar for each of these CBIRs, and the calculation of rankings is determined by the comparison of features (low-, mid-, high-level). Nevertheless, all things being equal, the respective realization leads to different results. Knowledge about the internal configuration (used features, weights and metrics) of these systems would be beneficial in many usage scenarios (e.g., by using a query image content sensitive query forwarding strategy or improved result ranking strategies in meta search engines). In this context, the paper presents an approach that supports an automatic detection of the configuration of CBIR systems. We demonstrate that the problem can be partly traced back to an optimization problem and tested several optimization algorithms. The approach has been evaluated based on the ImageCLEF test set and shows good results.