An Adaptive System of Classification and Qualitative Interpretation of the Date of Remote Sensing of Water Surface

The problem of classification of terrestrial landscapes and aquatories basing on the remote measurements is one of important among them. Various algorithms of the theory of images recognition, statistical decisions and cluster analysis are used to solve this problem. The problem of recognition consists in the divide of some group of objects by classes with the certain requirements. The objects having objectively general properties are related to one class. An initial data for the solution of a recognition problem are results of some observations or the direct measurements, that are named initial attributes. Feature of remote measurements is collection of the information when the data of measurements achieving the data processing system belong to the traces of flying system. As result the two dimensional image of investigated object is registered. Statistical model of spottiness for investigated space is one of models of this image. In real conditions, the research of spots, the reception of their statistical characteristics and their use in a problem of detection is enough a complex problem. It is necessary to develop the criteria allowing to distinguish the spots from other phenomena. For example, it is necessary to determine such threshold the exceeding of which is the spot indicator. Also it is necessary to develop modeling representation of processes of spots detection. The mathematical model parametrizing the phone characteristics of water surface spottiness is proposed. Relative software is realized. The results of the software application of the satellite data processing for the Atlantic and Pacific regions are given.