Publications

@article{guerrero-curieses_cost-sensitive_2009,

title = {Cost-sensitive and modular land-cover classification based on posterior probability estimates},

author = {Alicia Guerrero-Curieses and Rocío Alaiz-Rodríguez and Jesús Cid-Sueiro},

url = {https://www.tandfonline.com/doi/abs/10.1080/01431160902787695},

year  = {2009},

date = {2009-01-01},

urldate = {2009-01-01},

journal = {International Journal of Remote Sensing},

volume = {30},

number = {22},

pages = {5877–5899},

abstract = {This paper proposes a modular approach for land-cover classification from satellite images, focusing learning on the decision boundary using posterior probability estimates. A self-configuring architecture addresses class conflicts, and the learning algorithm prioritizes critical probability regions based on user-defined misclassification costs. Additionally, filtering the posterior probability map helps reduce impulsive noise common in automatic classification. Experiments on multi- and hyperspectral images demonstrate the method’s effectiveness compared to approaches like Support Vector Machines.},

note = {Publisher: Taylor & Francis},

keywords = {Decision Boundary Learning, Hyperspectral Imaging, Land-cover Classification, Posterior Probability Estimation, Satellite Imagery},

pubstate = {published},

tppubtype = {article}

}