Contextual Image Classification based on multi spatiotemporal data. It define the classifiers based on the log posterior probabilities on the neighborhoods calculated respective training data sets, and combine the classifiers by minimizing the averaged risk function. Classification of test data can be executed non-iteratively, and the method is very fast in computation and shows a good performance. Contextual means this approach is focusing on the relationship of the nearby pixels, which is also called neighbourhood. The goal of this approach is to classify the images by using the contextual information.