
Optical Character Recognition (OCR) and Machine Learning with Ahmad Anis - ML 086
Adventures in Machine Learning
00:00
Boosting the Performance of Multi-Threading Multi-Processing on Small Hardware
So another step when people dealing with bandwidth work was that they do not actually need to perform the operation or the operation or any other operation on every frame. So we do have a margin that we can skip some frames and we can get that desired result. We just in the first adversion we just localized that part and we can use different techniques like template matching so if our background is not changing very much we can use template matching and it works well on kinks which are static. Using this sort of technique they actually saved us lot of time so we did not have to OCR on every single frame instead we just OCR to understand in which the tracker was filled yeah I really like where
Transcript
Play full episode