Hello everyone, I hope you are well ! I am currently testing tesseract.js with node.js to extract information from ID cards. But I noticed that the recognition is still not efficient and varies depending on the quality of the image. My goal in reality is to be able to extract the name, the first name, the date of birth, ... everything except the photo and the signature. Since on each card there is information which is fixed and only personal information varies. I wonder how I can create my own training model to dramatically improve recognition and extract only the information I need. Or are there beginner tutorials that can help me do it quickly?
Thanks for your help. -- 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 view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/f348333b-f63f-4fd2-bc1d-180ee952a5edn%40googlegroups.com.
