CINDI at ImageCLEF 2006: image retrieval & annotation tasks for the general photographic and medical image collections

Authors:
M. M. Rahman;V. Sood;B. C. Desai;P. Bhattacharya
Affiliations:
Dept. of Computer Science & Software Engineering, Concordia University, Canada;Dept. of Computer Science & Software Engineering, Concordia University, Canada;Dept. of Computer Science & Software Engineering, Concordia University, Canada;Concordia Institute for Information Systems Engineering, Concordia University, Canada
Venue:
CLEF'06 Proceedings of the 7th international conference on Cross-Language Evaluation Forum: evaluation of multilingual and multi-modal information retrieval
Year:
2006

Citing 8
Cited 2

Introduction to statistical pattern recognition (2nd ed.)

Introduction to statistical pattern recognition (2nd ed.)
On Combining Classifiers

IEEE Transactions on Pattern Analysis and Machine Intelligence
Content-Based Image Retrieval at the End of the Early Years

IEEE Transactions on Pattern Analysis and Machine Intelligence
Modern Information Retrieval

Modern Information Retrieval
Introduction to MPEG-7: Multimedia Content Description Interface

Introduction to MPEG-7: Multimedia Content Description Interface
Probability Estimates for Multi-class Classification by Pairwise Coupling

The Journal of Machine Learning Research
Relevance feedback: a power tool for interactive content-based image retrieval

IEEE Transactions on Circuits and Systems for Video Technology
Overview of the ImageCLEF 2006 photographic retrieval and object annotation tasks

CLEF'06 Proceedings of the 7th international conference on Cross-Language Evaluation Forum: evaluation of multilingual and multi-modal information retrieval

Meiji university at ImageCLEF2008 photo retrieval task: evaluation of image retrieval methods integrating different media

CLEF'08 Proceedings of the 9th Cross-language evaluation forum conference on Evaluating systems for multilingual and multimodal information access
Multimodal indexing based on semantic cohesion for image retrieval

Information Retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents the techniques and the analysis of different runs submitted by the CINDI group in ImageCLEF 2006. For the ad-hoc image retrieval from both the photographic and medical image collections, we experimented with cross-modal (image and text) interaction and integration approaches based on the relevance feedback in the form of textual query expansion and visual query point movement with adaptive similarity matching functions. For the automatic annotation tasks for both the medical and object collections, we experimented with a classifier combination approach, where several probabilistic multi-class support vector machine classifiers with features at different levels as inputs are combined to predict the final probability scores of each category as image annotation. Analysis of the results of the different runs we submitted for both the image retrieval and annotation tasks are reported in this paper.