Convolution of Images Using Deep Neural Networks in the Recognition of Footage Objects

Abstract

In the problems of image recognition, various approaches used when the image is noisy and there is a small sample of observations. The paper discusses nonparametric recognition methods and methods based on deep neural networks. This type of neural network allows you to collapse images, to perform downsampling as many times as necessary. Moreover, the image recognition speed is quite high, and the data dimension is reduced by using convolutional layers. One of the most important elements of the application of convolutional neural networks is training. The article gives the results of work on the application of convolutional neural networks. The work was carried out in several stages. In the first stage was carried out the modeling of the convolutional neural network and was developed its architecture. In the second stage, the neural network was trained. The third phase produced Python software. The software health check and video processing speed were then performed.