Combining of Image Classification With Probabilistic Neural Network (PNN) Approaches Based on Expectation Maximum (EM)

This paper presents the design of classifiers with neural network approach based on the method used Expectations Maximum (EM). The decision rule of Bayes classifier using the Minimum Error to the classification of a mixture of multitemporal imagery. In this particular, the multilayer perceptron neural network model with Probabilistic Neural Network (PNN) is used for nonparametric estimation of posterior class probabilities. Temporal image correlation calculated with the prior joint probabilities of each class that is automatically estimated by applying a special formula that is algorithm expectation maximum of multitemporal imagery. Experiments performed on two multitemporal image is the image of the Saguling taken at two different time. Based on experimental results on two test areas can be shown that the average accuracy rate PNN classifier is better than the Back Propagation (BP), and the Expectation Maximum (EM) increase the ability of classifiers. Multinomial PNN classifier by applying the maximum expected to have a consistent recognition capability for multitemporal imagery, and also consistent for each object class category. The proposed classification methodology can solve the problem multitemporal efectively.