Automation of Parsing Photographs from publicly accessible sources using neural networks

Abstract

This master's thesis presents the development of a data parsing system based on a convolutional neural network. Its purpose is to acquire and process a dataset of photographs from publicly accessible sources. The system tracks and classifies photographs based on the presence of medical masks and features a unique configuration and operational block, designed for use in machine learning processes to evaluate the gathered data. The development utilized the Python programming language, PyCharm and Jupyter Notebook development environments, and the tensorflow and docker model serving environments.