Comparative study on multispectral agricultural image classification using Bayesian and neural network approaches

In this comparative study, the Bayesian and a neural network (the HLVQ) approach are used to classify multispectral LANDSAT images. The studied area contains several agricultural classes (wheat, flax,...). Some classes are found to be non homogeneous and thus are divided in this study into several subclasses. The Gaussian assumption needed by the Bayesian classifier is thus justified by this division. The main result obtained in this study is that the Bayesian classifier and the neural network considered here provide equivalent solutions for the classification of agricultural multispectral images.

[1]  King-Sun Fu,et al.  Statistical pattern classification using contextual information , 1980 .

[2]  B. Solaiman,et al.  A hybrid algorithm (HLVQ) combining unsupervised and supervised learning approaches , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[3]  B. Solaiman,et al.  A comparative study of conventional and neural network classification of multispectral data , 1994, Proceedings of IGARSS '94 - 1994 IEEE International Geoscience and Remote Sensing Symposium.

[4]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .