Collaborative multi-strategy classification: application to per-pixel analysis of images

Authors:
Pierre Gançarski;Cédric Wemmert
Affiliations:
University Louis Pasteur, Strasbourg, France;University Louis Pasteur, Strasbourg, France
Venue:
MDM '05 Proceedings of the 6th international workshop on Multimedia data mining: mining integrated media and complex data
Year:
2005

Citing 12
Cited 0

A Validity Measure for Fuzzy Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
Bagging predictors

Machine Learning
On Combining Classifiers

IEEE Transactions on Pattern Analysis and Machine Intelligence
Data clustering: a review

ACM Computing Surveys (CSUR)
Cluster validity methods: part I

ACM SIGMOD Record
Techniques of Cluster Algorithms in Data Mining

Data Mining and Knowledge Discovery
An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants

Machine Learning
On Clustering Validation Techniques

Journal of Intelligent Information Systems
Knowledge Acquisition Via Incremental Conceptual Clustering

Machine Learning
Combining Classifiers by Constructive Induction

ECML '98 Proceedings of the 10th European Conference on Machine Learning
Boosting First-Order Learning

ALT '96 Proceedings of the 7th International Workshop on Algorithmic Learning Theory
Issues in stacked generalization

Journal of Artificial Intelligence Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new process of collaborative multi-step multi-strategy classification of complex data. Our goal is to be able to handle in the same system several instances of classifiers in order to make them collaborate. In this paper, we highlight how the classifiers collaborate. We present the implementation of our method dedicated to remote sensing images. Finally, we validate it with a pixel based classification application.