Аннотация:Pattern recognition problem is outlined in the context of remote sensing imagery processing
using textural and spectral features of the land surface objects. Main attention is paid to recognition of forests of different species and ages based on machine-learning algorithms and high-productive computers. We consider the maximum of the posterior probability principle in the Bayesian
classifier improvements and the formalism of Markov random fields for the neighborhood description of the pixels for the related classes of the forest objects. The improvements concern reaching stable solutions in the multi-class recognition based on a step-wise optimization approach, holdout cross-validation and resampling techniques. The energy category of the selected classes serves to account for the likelihood measure between the registered radiances and the theoretical distribution functions approximating remotely sensed data. Optimization procedures are undertaken to solve the pattern recognition problem of the texture description for the forest classes together with finding thin nuances of their spectral distribution in the feature space. As a result, possible redundancy of the channels for imaging spectrometer due to their correlations is removed.Difficulties are revealed due to different sampling data while separating pixels, which characterize the sunlit tops, shaded space and intermediate cases of the Sun illumination conditions on the hyperspectral images. Such separation of pixels for the forest classes is maintained to enhance the recognition accuracy, but learning ensembles of data need to be agreed for these categories of pixels.