A detailed comparison of backpropagation neural network and maximum-likelihood classifiers for urban land use classification

A detailed comparison of the backpropagation neural network and maximum-likelihood classifiers for urban land use classification is presented. Landsat Thematic Mapper images of Tucson, Arizona, and Oakland, California, were used for this comparison. For the Tucson image, the percentage of matching pixels in the two classification maps was only 64.5%, while for the Oakland image it was 83.3%. Although the test site accuracies of the two Tucson maps were similar, the map produced by the neural network was visually more accurate; this difference is explained by examining class regions and density plots in the decision space and the continuous likelihood values produced by both classifiers. For the Oakland scene, the two maps were visually and numerically similar, although the neural network was superior in suppression of mixed pixel classification errors. From this analysis, the authors conclude that the neural network is more robust to training site heterogeneity and the use of class labels for land use that are mixtures of land cover spectral signatures. The differences between the two algorithms may be viewed, in part, as the differences between nonparametric (neural network) and parametric (maximum-likelihood) classifiers. Computationally, the backpropagation neural network is at a serious disadvantage to maximum-likelihood, taking nearly an order of magnitude more computing time when implemented on a serial workstation. >

[1]  Robert A. Schowengerdt,et al.  A review and analysis of backpropagation neural networks for classification of remotely-sensed multi-spectral imagery , 1995 .

[2]  N. Campbell,et al.  Derivation and applications of probabilistic measures of class membership from the maximum-likelihood classification , 1992 .

[3]  Daniel L. Civco,et al.  Artificial Neural Networks for Land-Cover Classification and Mapping , 1993, Int. J. Geogr. Inf. Sci..

[4]  D.R. Hush,et al.  Progress in supervised neural networks , 1993, IEEE Signal Processing Magazine.

[5]  Jeffrey R. Key,et al.  Neural Network VS. Maximum Likelihood Classifications Of Spectral And Textural Features In Visible, Thermal, And Passive Microwave Data , 1990, 10th Annual International Symposium on Geoscience and Remote Sensing.

[6]  G. Mehldau,et al.  A C-extension for rule-based image classification systems , 1990 .

[7]  P. Dreyer Classification of land cover using optimized neural nets on SPOT data , 1993 .

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

[9]  Z. K. Liu,et al.  Classification of remotely-sensed image data using artificial neural networks , 1991 .

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

[11]  James R. Anderson,et al.  A land use and land cover classification system for use with remote sensor data , 1976 .

[12]  J. Key,et al.  Classification of merged AVHRR and SMMR Arctic data with neural networks , 1989 .

[13]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[14]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[15]  Richard K. Kiang,et al.  Classification of Remotely Sensed Data Using Ocr-Inspired Neural Network Techniques , 1992, [Proceedings] IGARSS '92 International Geoscience and Remote Sensing Symposium.

[16]  Horst Bischof,et al.  Multispectral classification of Landsat-images using neural networks , 1992, IEEE Trans. Geosci. Remote. Sens..

[17]  P. D. Heermann,et al.  Classification of multispectral remote sensing data using a back-propagation neural network , 1992, IEEE Trans. Geosci. Remote. Sens..

[18]  N. J. Mulder,et al.  Neural Networks Applied To The Classification Of Remotely Sensed Data , 1991, [Proceedings] IGARSS'91 Remote Sensing: Global Monitoring for Earth Management.

[19]  Maureen Caudill,et al.  Neural networks primer, part III , 1988 .

[20]  G. O. Moe,et al.  Multispectral image-processing with a three-layer backpropagation network , 1989, International 1989 Joint Conference on Neural Networks.

[21]  H. Gish,et al.  A probabilistic approach to the understanding and training of neural network classifiers , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[22]  Jon Atli Benediktsson,et al.  Classification Of Very High Dimensional Data Using Neural Networks , 1990, 10th Annual International Symposium on Geoscience and Remote Sensing.

[23]  Nicholas Short,et al.  Real-time expert system and neural network for the classification of remotely sensed data , 1991 .

[24]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[25]  Richard Lippmann,et al.  Neural Network Classifiers Estimate Bayesian a posteriori Probabilities , 1991, Neural Computation.

[26]  G.G. Wilkinson,et al.  Neural Network Classification Of Multi-date Satellite Imagery , 1991, [Proceedings] IGARSS'91 Remote Sensing: Global Monitoring for Earth Management.

[27]  Zhengkai Liu,et al.  A new approach to pattern recognition of remote sensing image using artificial neural network , 1993, Proceedings of IGARSS '93 - IEEE International Geoscience and Remote Sensing Symposium.

[28]  Robert A. Schowengerdt,et al.  A review and analysis of neural networks for classification of remotely sensed multispectral imagery , 1993 .

[29]  Adrian K. Fung,et al.  Sea Ice Classification Using Fast Learning Neural Networks , 1992, [Proceedings] IGARSS '92 International Geoscience and Remote Sensing Symposium.

[30]  G.G. Wilkinson,et al.  Integration of neural network and statistical image classification for land cover mapping , 1993, Proceedings of IGARSS '93 - IEEE International Geoscience and Remote Sensing Symposium.