Erscheint 12 Ausgaben pro Jahr
ISSN Druckformat: 0040-2508
ISSN Online: 1943-6009
Indexed in
INTELLECTUAL DATA PROCESSING AND SELF-ORGANIZATION OF STRUCTURAL FEATURES AT RECOGNITION OF VISUAL OBJECTS
ABSTRAKT
The issues of enhancing efficiency of the structural image recognition methods in the computer vision systems are discussed. For the purpose of compression of the space of signs it is suggested to perform self-learning with application of Kohonen network. As the result, it is developed a more efficient in terms of processing fast-action method of recognition based on cluster vector description of the standards. The computer simulation results are provided for estimation of the quality of recognition for a variety of processing options in the application image database.
-
Gorokhovatskyi Volodymyr, Gorokhovatskyi Oleksii, Yevgenyi Putyatin, Olena Peredrii, Quantization of the Space of Structural Image Features as a Way to Increase Recognition Performance, 2018 IEEE Second International Conference on Data Stream Mining & Processing (DSMP), 2018. Crossref