Assessing the classification accuracy of multisource remote sensing data

Classification accuracy has traditionally been expressed by the overall accuracy percentage computed from the sum of the diagonal elements of the error, confusion, or misclassification matrix resulting from the application of a classifier. This article assesses the adequacy of the overall accuracy measure and demonstrates that it can give misleading and contradictory results. The Kappa test statistic assesses interclassifier agreement and is applied in assessing the classification accuracy of two classifiers, a neural network and a decision tree model on the same data set. The Kappa statistic is shown to be a more discerning statistical tool for assessing the classification accuracy of different classifiers and has the added advantage of being statistically testable against the standard normal distribution. It gives the analyst better interclass discrimination that the overall accuracy measure. The authors recommend that the Kappa statistic be used in preference to the overall accuracy as a means of assessing classification accuracy.

[1]  George F. Hepner,et al.  Application of an artificial neural network to landcover classification of thematic mapper imagery , 1990 .

[2]  Scott E. Decatur,et al.  Application of neural networks to terrain classification , 1989, International 1989 Joint Conference on Neural Networks.

[3]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[4]  P. Swain,et al.  Neural Network Approaches Versus Statistical Methods In Classification Of Multisource Remote Sensing Data , 1990 .

[5]  Brian G. Lees,et al.  Decision-tree and rule-induction approach to integration of remotely sensed and GIS data in mapping vegetation in disturbed or hilly environments , 1991 .

[6]  J. Fleiss.  Statistical methods for rates and proportions , 1974 .

[7]  Xiaomei Xu,et al.  Applying neural net technology for multi-objective land use planning , 1991 .

[8]  George F. Hepner,et al.  Artificial neural network classification using a minimal training set - Comparison to conventional supervised classification , 1990 .

[9]  S. Davey,et al.  The environmental relationships of arboreal marsupials in a eucalypt forest : a basis for Australian forest wildlife management , 1989 .

[10]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[11]  P. D. Heermann,et al.  Application Of Neural Networks For Classification Of Multi-source Multi-spectral Remote Sensing Data , 1990, 10th Annual International Symposium on Geoscience and Remote Sensing.