I wanted to know if there is a way to extract hardcoded subtitles via OCR, should I do some image processing after extracting the frames in order to use
I have tried to extract frames from the video and remove everything that is not the color of the subtitles, but I got terrible results when using
Is it possible to get decent results only using some workaround like this or should I rather train
tesseract myself? It is easy to generate training data from random quotes added on random movie pictures with random fonts but it will require a lot of time to train it.