The neuronal identification of pictorial data, with special emphasis on both quantitative & qualitative analysis, is more frequently utilized to gain & deepen the empirical data knowledge. Extraction & then classification of selected picture features, enables one to create computer tools in order to identify these objects presented as, for example, digital pictures. In relationship from this, it seems to be purposeful the search of the modern methods helping educational process in the range of construction as well as exploitation of neuronal models in context of their utilization in picture analysis process. The additional aim of the work was the comparison of neural network of the type MLP and RBF for indication of the optimum classification tool.