Method for Visual Video Defects Detection using Machine Learning.

The main problem to be solved by this research is the imperfection of the video testing process. Nowadays this process involves mainly manual testing, which is inefficient due to the high probability of human errors, significant time, and material costs. In order to improve this process, we have created a convolutional neural network that can detect defects in video frames with high probability. We have also built a prototype of a software system that can automatically detect defects in video using the created and trained convolutional neural network.