THE SPEED CALCULATING INCREASING METHOD OF THE MARKOV MODEL NETWORK NODE

The subject of this research is the image classification methods based on a set key points descriptors. goal to increase performance methods, in particular, improve time characteristics by introducing hashing tools for reference data representation. Methods used: ORB detector and descriptors, tools, search arrays, metrics-based apparatus determining relevance vectors, software modeling. obtained results: developed an effective method introduction high-speed using hash structures, which speeds up calculation dozens times; considered experimental descriptions increases linearly with decreasing number hashes; minimum metric value limit choice setting class object descriptors significantly affects accuracy classification; such can be optimized fixed samples databases; experimentally achieved indicates efficiency proposed hashing. practical significance work - model’s synthesis representations space, proof classifiers modifications examples, development applied models implementing computer vision systems.