No abstract

No abstract

No abstract

No abstract

In the article it is shown that for the operative estimation and analysis of optical images of objects of plants using spectral characteristics in the optical range, data have considerable volumes. The data is represented by an additive color model in RGB format, which requires significant numerable resources for their use in neural networks. It is proposed instead of a large sample size on the input of the neural network to provide statistical characteristics of the sample, which reduces the numerable resource, while adequately representing the image. Постановка проблеми. З розвитком обчислювальної техніки стало можли-вим вирішити ряд завдань, що виникають у процесі управління об'єктами