@inproceedings{allili_unsupervised_2010,

title = {Unsupervised feature selection and learning for image segmentation},

author = {M. S. Allili and D. Ziou and N. Bouguila and S. Boutemedjet},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-77954407977&doi=10.1109%2fCRV.2010.44&partnerID=40&md5=a7d8e3147216429f18ef7af3167acb42},

doi = {10.1109/CRV.2010.44},

isbn = {978-0-7695-4040-5},

year  = {2010},

date = {2010-01-01},

booktitle = {CRV 2010 - 7th Canadian Conference on Computer and Robot Vision},

pages = {285–292},

address = {Ottawa, ON},

abstract = {In this paper we investigate the integration of feature selection in segmentation through an unsupervised learning approach. We propose a clustering algorithm that efficiently mitigates image under/over-segmentation, by combining generalized Gaussian mixture modeling and feature selection. The algorithm is based on generalized Gaussian mixture modeling which is less prone to region number over-estimation in case of noisy and heavy-tailed image distributions. On the other hand, our feature selection mechanism allows to automatically discard uninformative features, which leads to better discrimination and localization of regions in high-dimensional spaces. Experimental results on a large database of real-world images showed us the effectiveness of the proposed approach. © 2010 IEEE.},

keywords = {Clustering algorithms, Computer vision, Evolutionary algorithms, Feature extraction, Feature selection, Gaussian distribution, Generalized Gaussian, Generalized Gaussian Distributions, Heavy-tailed, High dimensional spaces, Image distributions, Image segmentation, Large database, Over-estimation, Real-world image, Unsupervised feature selection},

pubstate = {published},

tppubtype = {inproceedings}

}