Closed Kunal2341 closed 4 years ago
You're better off asking on StackOverflow as this is a tesseract api-related question. Try reading tesseract's documentation for a method to extract word attributes (such as bold, color, etc) and you should be able to call them via tesserocr (if not then feel free to open an issue).
So I have a document full of text. Is there any way that I can detect bold or special kinds of text. Maybe detect colors, or size of the text. Could someone help me with how to do this? Anything will help. Thanks