Рақамли технологияларнинг назарий ва амалий масалалари 7-том 3-нөмір (2024) · 92-98-беттер
Optimization of image recognition of pollen grains based on parametric identification
Жуманов, Исраил, Сафаров, Рустам
Аңдатпа
Methods have been developed to optimize the identification of pollen grains using statistical, dynamic, textural and specific image characteristics. Mechanisms for point and nonlinear verification of the correspondence of the contours of the input and reference objects - pollen grains, as well as for adjusting the parameters of raster images have been studied and proposed. Implemented mechanisms for reducing contour zero points, reducing raster dimensions, scaling, threshold and level control, encoding and placing images of micro-objects based on a pyramidal model, selecting contour reference points, cognitive analysis, searching for points with annealing, prohibition, based on stochastic modeling using a truncated chain Markova. A set of programs for identification, recognition, classification and systematization of pollen grains was implemented in C++ in the parallel computing environment “CUDA”.
идентификацияизображениепыльцевое зернораспознаваниеклассификацияэффективностьпогрешностьтрудоемкостькомплекс программidentification
Метадеректер дереккөзі: журналдың OAI-PMH архиві · Sindex толық мәтінді сақтамайды, дереккөзге сілтеме береді.