Unsupervised feature selection applied to SPOT5 satellite images indexing

Marine Campedel, Ivan Kyrgyzov, Henri Maitre
Proceedings of the Workshop on New Challenges for Feature Selection in Data Mining and Knowledge Discovery at ECML/PKDD 2008, PMLR 4:48-59, 2008.

Abstract

Satellite images are numerous and weakly exploited: it is urgent to develop efficient and fast indexing algorithms to facilitate their access. In order to determinate the best features to be extracted, we propose a methodology based on automatic feature selection algorithms, applied unsupervisingly on a strongly redundant features set. In this article we also demonstrate the usefulness of consensus clustering as a feature selection algorithm, allowing selected number of features estimation and exploration facilities. The efficiency of our approach is demonstrated on SPOT5 images.

Cite this Paper


BibTeX
@InProceedings{pmlr-v4-campedel08a, title = {Unsupervised feature selection applied to SPOT5 satellite images indexing}, author = {Campedel, Marine and Kyrgyzov, Ivan and Maitre, Henri}, booktitle = {Proceedings of the Workshop on New Challenges for Feature Selection in Data Mining and Knowledge Discovery at ECML/PKDD 2008}, pages = {48--59}, year = {2008}, editor = {Saeys, Yvan and Liu, Huan and Inza, Iñaki and Wehenkel, Louis and Pee, Yves Van de}, volume = {4}, series = {Proceedings of Machine Learning Research}, address = {Antwerp, Belgium}, month = {15 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v4/campedel08a/campedel08a.pdf}, url = {https://proceedings.mlr.press/v4/campedel08a.html}, abstract = {Satellite images are numerous and weakly exploited: it is urgent to develop efficient and fast indexing algorithms to facilitate their access. In order to determinate the best features to be extracted, we propose a methodology based on automatic feature selection algorithms, applied unsupervisingly on a strongly redundant features set. In this article we also demonstrate the usefulness of consensus clustering as a feature selection algorithm, allowing selected number of features estimation and exploration facilities. The efficiency of our approach is demonstrated on SPOT5 images.} }
Endnote
%0 Conference Paper %T Unsupervised feature selection applied to SPOT5 satellite images indexing %A Marine Campedel %A Ivan Kyrgyzov %A Henri Maitre %B Proceedings of the Workshop on New Challenges for Feature Selection in Data Mining and Knowledge Discovery at ECML/PKDD 2008 %C Proceedings of Machine Learning Research %D 2008 %E Yvan Saeys %E Huan Liu %E Iñaki Inza %E Louis Wehenkel %E Yves Van de Pee %F pmlr-v4-campedel08a %I PMLR %P 48--59 %U https://proceedings.mlr.press/v4/campedel08a.html %V 4 %X Satellite images are numerous and weakly exploited: it is urgent to develop efficient and fast indexing algorithms to facilitate their access. In order to determinate the best features to be extracted, we propose a methodology based on automatic feature selection algorithms, applied unsupervisingly on a strongly redundant features set. In this article we also demonstrate the usefulness of consensus clustering as a feature selection algorithm, allowing selected number of features estimation and exploration facilities. The efficiency of our approach is demonstrated on SPOT5 images.
RIS
TY - CPAPER TI - Unsupervised feature selection applied to SPOT5 satellite images indexing AU - Marine Campedel AU - Ivan Kyrgyzov AU - Henri Maitre BT - Proceedings of the Workshop on New Challenges for Feature Selection in Data Mining and Knowledge Discovery at ECML/PKDD 2008 DA - 2008/09/11 ED - Yvan Saeys ED - Huan Liu ED - Iñaki Inza ED - Louis Wehenkel ED - Yves Van de Pee ID - pmlr-v4-campedel08a PB - PMLR DP - Proceedings of Machine Learning Research VL - 4 SP - 48 EP - 59 L1 - http://proceedings.mlr.press/v4/campedel08a/campedel08a.pdf UR - https://proceedings.mlr.press/v4/campedel08a.html AB - Satellite images are numerous and weakly exploited: it is urgent to develop efficient and fast indexing algorithms to facilitate their access. In order to determinate the best features to be extracted, we propose a methodology based on automatic feature selection algorithms, applied unsupervisingly on a strongly redundant features set. In this article we also demonstrate the usefulness of consensus clustering as a feature selection algorithm, allowing selected number of features estimation and exploration facilities. The efficiency of our approach is demonstrated on SPOT5 images. ER -
APA
Campedel, M., Kyrgyzov, I. & Maitre, H.. (2008). Unsupervised feature selection applied to SPOT5 satellite images indexing. Proceedings of the Workshop on New Challenges for Feature Selection in Data Mining and Knowledge Discovery at ECML/PKDD 2008, in Proceedings of Machine Learning Research 4:48-59 Available from https://proceedings.mlr.press/v4/campedel08a.html.

Related Material