DocumentCode :
3536235
Title :
Active learning for classification of remote sensing images
Author :
Bruzzone, Lorenzo ; Persello, Claudio
Author_Institution :
Dept. of Inf. Eng. & Comput. Sci., Univ. of Trento, Trento, Italy
Volume :
3
fYear :
2009
fDate :
12-17 July 2009
Abstract :
This paper presents an analysis of active learning techniques for the classification of remote sensing images and proposes a novel active learning method based on support vector machines (SVMs). The proposed method exploits a query function for the inclusion of batches of unlabeled samples in the training set, which is based on the evaluation of two criteria: uncertainty and diversity. This query function adopts a stochastic approach to the selection of unlabeled samples, which is based on a function of uncertainty estimated from the distribution of errors on the validation set (which is assumed available for the model selection of the SVM classifier). Experimental results carried out on a very high resolution image confirm the effectiveness of the proposed active learning technique, which results more accurate than standard methods.
Keywords :
geophysical image processing; image classification; learning (artificial intelligence); remote sensing; support vector machines; active learning techniques; automatic classification; high resolution image; image classification; machine learning; remote sensing images; semisupervised learning; stochastic analysis; support vector machines; unlabeled samples; Computer science; Electronic mail; Image analysis; Labeling; Learning systems; Machine learning; Remote sensing; Support vector machine classification; Support vector machines; Uncertainty; Automatic classification; active learning; machine learning remote sensing; semisupervised learning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Geoscience and Remote Sensing Symposium,2009 IEEE International,IGARSS 2009
Conference_Location :
Cape Town
Print_ISBN :
978-1-4244-3394-0
Electronic_ISBN :
978-1-4244-3395-7
Type :
conf
DOI :
10.1109/IGARSS.2009.5417857
Filename :
5417857
Link To Document :
بازگشت