Hello, I m inexperienced in OCR with tesseract.
i was thinking about writing a small application that is able to recognize text over a video feed taken from webcams (phone/laptop). However i have tried online version (https://tesseract.projectnaptha.com/) and its does not look fast enough for this specific usage. I have read earlier that one of the factor of the speed is the size (px) of the input. I wonder if there are more parameters that could change this behavior in a good way. I had some ideas, but i m unsure that they are meaningful, - use a specific trained model for one specific font, - a smaller alphabet, - a smaller range of font sizes, Could it help ? Are there other parameters i might investigate ? I also wonder which has the most impact on the speed between recognition and preprocessing ? As i want to read a video feed from webcam, i must assume preprocessing will be required and i m afraid heavy. However the example i have linked above does not seem to require much preprocessing. thanks for your inputs. -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to tesseract-ocr+unsubscr...@googlegroups.com. To post to this group, send email to tesseract-ocr@googlegroups.com. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/88959387-45c0-45b1-8d7a-15638775e670%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
