I'm trying to read the following images using pyTessaract.
The program I've made extracts these images from a video, I want to use pytessaract to extract text from them. The program also has the option to make boxes at the areas I want to the OCR to look at, it then crops the image at those places and runs OCR.
But still the output is not very accurate sometimes I get random letters / text included in the output, sometimes the text is completely random. It's just not detecting the text. How can I improve the detection ? Is there some preprocessing strategy I can use ? Or anything else ?