Identification of Product Non-Conformities Using Computer Vision Algorithms

Abstract

The implementation of computer vision in the process of identifying non-conforming products, as well as the application of technologies based on Internet networks, deep learning, large databases within the manufacturing industry leads to the emergence of quality 4.0. Today, the application of computer vision as well as non-conformity detection algorithms in the manufacturing industry can be seen as technological pillars of quality 4.0, which is in direct connection with the company's operations. The main goal of the work is the development of a system for identifying non-compliant products within the manufacturing industry, where the focus is on the application of technologies based on computer vision. The secondary goal of the work refers to the reduction of the necessary funds for the implementation of the system on production machines, the development of a universal, flexible system, where the timely identification of non-compliant products will reduce the company's losses.