Cost-sensitive and modular land-cover classification based on posterior probability estimates

References

• Agrawal , A. , Kumar , N. and Radhakrishna , M. 2007 . Multispectral image classification: a supervised neural computation approach based on rough-fuzzy membership function and weak fuzzy similarity relation . International Journal of Remote Sensing , 28 : 4597 – 4608 .
   Web of Science ®Google Scholar
• Alba , J. , Docío , L. , Docampo , D. and Márquez , O. 1999 . Growing mixtures network for classification applications . Signal Processing , 76 : 43 – 60 .
   Web of Science ®Google Scholar
• Arriaza , J. T. , Rojas , F. G. , López , M. P. and Cantón , M. 2003 . An automatic cloud-masking system using backpro neural nets for AVHRR scenes . IEEE Transactions on Geoscience and Remote Sensing , 41 : 826 – 831 .
   Web of Science ®Google Scholar
• Arribas , J. and Cid-Sueiro , J. 2005 . A model selection algorithm for a posteriori probability estimation with neural networks . IEEE Transactions on Neural Networks , 16 : 799 – 809 .
   PubMed Web of Science ®Google Scholar
• Benediktsson , J. , Palmason , J. and Sveinsson , J. 2005 . Classification of hyperspectral data from urban areas based on extended morphological profiles . IEEE Transactions on Geoscience and Remote Sensing , 43 : 480 – 491 .
   Web of Science ®Google Scholar
• Berardi , V. and Zhang , G. 1999 . The effect of misclassification costs on neural network classifiers . Decision Sciences , 30 : 659 – 682 .
   Web of Science ®Google Scholar
• Bischof , H. and Leonardis , A. 1998 . Finding optimal neural networks for land use classification . IEEE Transactions on Geoscience and Remote Sensing , 36 : 337 – 341 .
   Web of Science ®Google Scholar
• Bischof , H. , Schneider , W. and Pinz , A. 1992 . Multispectral classification of Landsat images using neural networks . IEEE Transactions on Geoscience and Remote Sensing , 30 : 482 – 490 .
   Web of Science ®Google Scholar
• Bobrowsky , L. and Sklansky , J. 1995 . Linear classifiers by window training . IEEE Transactions on System Science and Cybernetics , 25 : 1 – 9 .
   Web of Science ®Google Scholar
• Bogdanov , A. , Sandven , S. , Johannessen , O. , Alexandrov , V. and Bobylev , L. 2005 . Multisensor approach to automated classification of sea ice image data . IEEE Transactions on Geoscience and Remote Sensing , 43 : 1648 – 1664 .
   Web of Science ®Google Scholar
• Bradford , J. , Kunz , C. , Kohavi , C. , Brunk , R. and Brodley , C. 1998 . Pruning Decision Trees with Misclassification Costs, Lecture Notes in Artificial Intelligence , Berlin : Springer-Verlag .
   Google Scholar
• Bruzzone , L. 2000 . An approach to feature selection and classification of remote sensing images based on the Bayes rule for minimum cost . IEEE Transactions on Geoscience and Remote Sensing , 38 : 429 – 438 .
   Web of Science ®Google Scholar
• Bruzzone , L. , Marconcini , M. , Wegmuller , U. and Wiesmann , A. 2004 . An advanced system for the automatic classification of multitemporal sar images . IEEE Transactions on Geoscience and Remote Sensing , 42 : 1321 – 1334 .
   Web of Science ®Google Scholar
• Camps-Valls , G. and Bruzzone , L. 2005 . Kernel-based methods for hyperspectral image classification . IEEE Transactions on Geoscience and Remote Sensing , 43 : 1351 – 1362 .
   Web of Science ®Google Scholar
• Christodoulou , C. , Michaelides , S. and Pattichis , C. 2003 . Multifeature texture analysis for the classification of clouds in satellite imagery . IEEE Transactions on Geoscience and Remote Sensing , 41 : 2662 – 2668 .
   Web of Science ®Google Scholar
• Cid-Sueiro , J. and Sancho-Gómez , J. 2001 . Satured perceptrons for maximum margin and minimum misclassification error . Neural Processing Letters , 14 : 217 – 226 .
   Web of Science ®Google Scholar
• Congalton , R. G. 1991 . A review of assessing the accuracy of classifications of remotely sensed data . Remote Sensing of Environment , 37 : 35 – 46 .
   Web of Science ®Google Scholar
• Dixon , D. and Candade , N. 2008 . Multispectral landuse classification using neural networks and support vector machines: one or the other, or both . International Journal of Remote Sensing , 29 : 1185 – 1206 .
   Web of Science ®Google Scholar
• Do-Tu , H. and Installe , M. 1978 . Learning algorithms for non-parametric solution to be minimum error classification problem . IEEE Transactions on Computers , 27 : 648 – 659 .
   Web of Science ®Google Scholar
• Duda , R. and Hart , P. 1973 . Pattern Classification and Scene Analysis , New York : John Wiley .
   Google Scholar
• Fang , H. and Liang , S. 2003 . Retrieving leaf area index with a neural network method: Simulation and validation . IEEE Transactions on Geoscience and Remote Sensing , 41 : 2052 – 2062 .
   Web of Science ®Google Scholar
• Foody , G. M. 2008 . RVM-based multi-class classification of remotely sensed data . International Journal of Remote Sensing , 29 : 1817 – 1823 .
   Web of Science ®Google Scholar
• Foody , G. M. and Cox , D. P. 1994 . Sub-pixel land cover composition estimation using a linear mixture model and fuzzy membership fucntions . International Journal of Remote Sensing , 15 : 619 – 631 .
   Web of Science ®Google Scholar
• Frate , F. D. and Solimini , D. 2004 . On neural network algorithms for retrieving forest biomass from SAR data . IEEE Transactions on Geoscience and Remote Sensing , 42 : 24 – 34 .
   Web of Science ®Google Scholar
• Fukunaga , K. 1990 . Introduction to Statistical Pattern Recognition , 2nd , San Diego : Academic Press .
   Google Scholar
• Guerrero-Curieses , A. , Alaiz-Rodriguez , R. and Cid-Sueiro , J. 2005 . Loss functions to combine learning and decision in multiclass problems . Neurocomputing , 69 : 3 – 17 .
   Web of Science ®Google Scholar
• Guerrero-Curieses , A. , Cid-Sueiro , J. , Alaiz-Rodriguez , R. and Figueiras-Vidal , A. 2004 . Local estimation of posterior class probabilities to minimize classification errors . IEEE Transactions on Neural Networks , 15 : 309 – 317 .
   PubMed Web of Science ®Google Scholar
• Hassibi, B. and Stork, D., 1993, Second order derivatives for network pruning: Optimal brain surgeon. In Advances in Neural Information Processing Systems, Vol. 5, S.J. Hanson, J.D. Cowan, and C.L. Giles, (Eds.) (San Mateo, CA: Morgan Kaufmann), pp. 164–171. Available online at http://citeseer.nj.nec.com/hassibi93second.html
   Google Scholar
• Hong , S. , Moon , W. , Hong-Yul , P. and Choi , G.-H. 2002 . Data fusion of multiple polarimetric SAR images using discrete wavelet transform (DWT) . IEEE International Geoscience and Remote Sensing Symposium, June 2002; IGARSS ′02 , 6 June : 3323 – 3325 .
   Google Scholar
• Jensen , J. , Qiu , F. and Patterson , K. 2001 . A neural network image interpretation system to extract rural and urban land use and land cover information from remote sensor data . Geocarto International , 16 : 1 – 10 .
   Google Scholar
• Joachims , T. 1999 . Making large-scale SVM learning practical. Advances in kernel methods – support vector learning. Technical Report , Edited by: Schölkopf , B. , Burges , C. and Smola , A. Cambridge, MA : MIT Press .
   Google Scholar
• Juang , B. and Katagiri , S. 1992 . Discriminative learning for minimum error classification . IEEE Transactions on Signal Processing , 40 : 3043 – 3054 .
   Web of Science ®Google Scholar
• Kulkarni , A. and McCaslin , S. 2004 . Knowledge discovery from multispectral satellite images . IEEE Geoscience and Remote Sensing Letters , 1 : 246 – 250 .
   Web of Science ®Google Scholar
• Kumar , A. , Basu , S. and Majumdar , K. 1997 . Robust classification of multispectral data using multiple neural networks and fuzzy integral . IEEE Transactions on Geoscience and Remote Sensing , 35 : 787 – 790 .
   Web of Science ®Google Scholar
• Lecun, Y., Denker, J., Solla, S., Howard, R. and Jackel, L., 1990, Optimal brain damage. In Advances in Neural Information Processing Systems II, D.S. Touretzky (Ed.) (San Mateo, CA: Morgan Kauffman). Available online at http://citeseer.nj.nec.com/lecun90optimal.html
   Google Scholar
• Li , Z. , Khananian , A. , Fraser , R. and Cihlar , J. 2001 . Automatic detection of fire smoke using artificial neural networks and threshold approaches applied to AVHRR imagery . IEEE Transactions on Geoscience and Remote Sensing , 39 : 1859 – 1870 .
   Web of Science ®Google Scholar
• Liu , C. , Frazier , P. and Kumar , L. 2007 . Comparative assessment of the measures of thematic classification accuracy . Remote Sensing of Environment , 107 : 606 – 616 .
   Web of Science ®Google Scholar
• Margineantu , D. and Dietterich , T. . Bootstrap methods for the cost-sensitive evaluation of classifiers . Proceedings of 17th International Conference on Machine Learning . San Francisco, CA. pp. 583 – 590 . Morgan Kaufmann .
   Google Scholar
• Melgani , F. and Bruzzone , L. 2004 . Classification of hyperspectral remote-sensing images with support vector machines . IEEE Transactions on Geoscience and Remote Sensing , 42 : 1778 – 1790 .
   Web of Science ®Google Scholar
• Mercier , G. , Hubert-Moy , L. , Houet , T. and Gouéry , P. 2005 . Estimation and monitoring of bare soil/vegetation ratio with spot vegetation and HRVIR . IEEE Transactions on Geoscience and Remote Sensing , 43 : 348 – 354 .
   Web of Science ®Google Scholar
• Miller , J. , Goodman , R. and Smyth , P. . Objective functions for probability estimation . Proceedings of the International Conference on Neural Networks . Vol. 1 , pp. 881 – 886 .
   Google Scholar
• Muchoney , D. and Williamson , J. 2001 . A Gaussian adaptive resonance theory neural network classification algorithm applied to supervised land cover mapping using multitemporal vegetation index data . IEEE Transactions on Geoscience and Remote Sensing , 39 : 1969 – 1977 .
   Web of Science ®Google Scholar
• Oti , K. , Uenishi , T. M. , Omasa , K. and Tamura , M. 2004 . Accuracy of land cover area estimated from coarse spatial resolution images using an unmixing method . International Journal of Remote Sensing , 25 : 1673 – 1683 .
   Web of Science ®Google Scholar
• Pazzani , M. , Merz , C. , Murphy , P. , Ali , K. , Hume , T. and Brunk , C. . Reducing misclassification costs . Proceedings of the 11th International Conference on Machine Learning . San Francisco, CA. pp. 217 – 225 . M. Kaufmann .
   Google Scholar
• Pearlmutter , B. and Hampshire , J. 1990 . “ Equivalence proofs for multilayer perceptron classifiers and the Bayesian discriminant function ” . In Proceedings of 1990 Connectionist Models Summer School , 159 – 172 . San Diego, CA : Morgan Kauffmann .
   Google Scholar
• Pellizzeri , T. , Oliver , C. , Lombardo , P. and Bucciarelli , T. 2002 . Improved classification of SAR images by segmentation and fusion with optical images . RADAR 2002 , 15–17 October 2002 : 158 – 161 .
   Google Scholar
• Pesaresi , M. and Benesiktsson , J. 2001 . A new approach for the morphological segmentation of high-resolution satellite imagery . IEEE Transactions on Geoscience and Remote Sensing , 39 : 309 – 320 .
   Web of Science ®Google Scholar
• Pohl , C. and Genderen , J. V. 1998 . Multisensor image fusion in remote sensing: concepts, methods and applications . International Journal of Remote Sensing , 19 : 823 – 854 .
   Web of Science ®Google Scholar
• Poirazi , P. , Neocleous , C. , Pattichis , C. and Schizas , C. 2004 . Classification capacity of a modular neural network implementing neurally inspired architecture and training rules . IEEE Transactions on Neural Networks , 15 : 597 – 612 .
   PubMed Web of Science ®Google Scholar
• Qian , Y. , Zhang , K. and Qiu , F. . Spatial contextual noise removal for post classification smoothing of remotely sensed images . Proceedings of the 2005 ACM Symposium on Applied Computing . Santa Fe, New Mexico. pp. 524 – 528 . New York : ACM .
   Google Scholar
• Raudys , S. 1998 . Evolution and generalization of a single neurone I. Single layer perceptron as seven statistical classifiers . Neural Networks , 11 : 283 – 296 .
   PubMed Web of Science ®Google Scholar
• Raudys , S. 1998 . Evolution and generalization of a single neurone II. Complexity of statistical classifiers and sample size considerations . Neural Networks , 11 : 297 – 313 .
   PubMed Web of Science ®Google Scholar
• Richard , M. and Lippmann , R. 1991 . Neural network classifiers estimate Bayesian a posteriori probabilities . Neural Computation , 3 : 461 – 483 .
   PubMed Web of Science ®Google Scholar
• Rizvi , S. and Nasrabadi , N. 2003 . Fusion techniques for automatic target recognition . Proceedings 32nd Applied Imagery Pattern Recognition Workshop , 15–17 October 2003 : 27 – 32 .
   Google Scholar
• Ruck , D. , Rogers , S. , Kabrisky , M. , Oxley , M. and Suter , B. 1990 . The multilayer perceptron as an approximation to a Bayes optimal discriminant function . IEEE Transactions on Neural Networks , 1 : 296 – 298 .
   PubMedGoogle Scholar
• Serpico , S. , Bruzzone , L. and Roli , F. 1996 . An experimental comparison of neural and statistical non-parametric algorithms for supervised classification of remote-sensing images . Pattern Recognition Letters , 17 : 1331 – 1341 .
   Web of Science ®Google Scholar
• Smits , P. , Dellepiane , S. and Schowengerdt , R. 1999 . Quality assesment of image classification algorithms for land-cover mapping: A review and a proposal for a cost-based approach . International Journal of Remote Sensing , 20 : 1461 – 1486 .
   Web of Science ®Google Scholar
• Soille , P. 2003 . Morphological Image Analysis: Principles and Applications , 2nd , Berlin : Springer-Verlag .
   Google Scholar
• Soille , P. and Pesaresi , M. 2002 . Advances in mathematical morphology applied to geoscience and remote sensing . IEEE Transactions on Geoscience and Remote Sensing , 40 : 2042 – 2055 .
   Web of Science ®Google Scholar
• Solaiman , B. , Koffi , R. , Mouchot , M. and Hillion , A. 1998 . An information fusion method for multispectral image classification postprocessing . IEEE Transactions on Geoscience and Remote Sensing , 36 : 395 – 406 .
   Web of Science ®Google Scholar
• Srivastava , A. , Oza , N. and Stroeve , J. 2005 . Virtual sensors: Using data mining techniques to efficiently estimate remote sensing spectra . IEEE Transactions on Geoscience and Remote Sensing , 43 : 590 – 600 .
   Web of Science ®Google Scholar
• Tian , B. and Azimi-Sadjadi , M. 2001 . Comparison of two different PNN training approaches for satellite cloud data classification . IEEE Transactions on Neural Networks , 12 : 164 – 168 .
   PubMed Web of Science ®Google Scholar
• Tian , B. , Shaikh , M. , Azimi-Sadjadi , M. , Haar , T. and Reinke , D. 1999 . A study of cloud classification with neural networks using spectral and textural features . IEEE Transactions on Neural Networks , 10 : 138 – 151 .
   PubMed Web of Science ®Google Scholar
• Tomas , I. 1980 . Spatial postprocessing of spectrally classified landsat data . Photogrammetic Engineering and Remote Sensing , 46 : 1201 – 1206 .
   Web of Science ®Google Scholar
• Ton , J. , Sticklen , J. and Jain , A. 1991 . Knowledge-based segmentation of Landsat images . IEEE Transactions on Geoscience and Remote Sensing , 29 : 222 – 231 .
   Web of Science ®Google Scholar
• Townshend , J. 1986 . The enhancement of computer classification by logical smoothing . Photogrammetic Engineering and Remote Sensing , 52 : 213 – 221 .
   Web of Science ®Google Scholar
• Vapnik , V. 1995 . The Nature of the Statistical Learning Theory , New York : Springer-Verlag .
   Google Scholar
• Verhoeye , J. and Wulf , R. D. 2002 . Land cover mapping at sub-pixel scales using linear optimization techniques . Remote Sensing of Environment , 79 : 96 – 104 .
   Web of Science ®Google Scholar
• Zellner , A. 1986 . Bayesian estimation and prediction using asymmetric loss functions . Journal of the American Statistical Association , 81 : 446 – 451 .
   Web of Science ®Google Scholar
• Zhang , Y. 2001 . Detection of urban housing development by fusing multisensor satellite data and performing spatial feature post-classification . International Journal of Remote Sensing , 22 : 3339 – 3355 .
   Web of Science ®Google Scholar