Hello, I am trying to use tesseract to OCR image files like this: http://imgur.com/1cffl
Using the english training data that comes bundled with tesseract, and limiting the recognized chars to "0123456789,." in a tesseract config file I get this output: http://pastebin.com/0vsDw3mL What would be the best approach to improve these results? - Try to find out what is the font being used on these images, build an image of numbers using that font, and train tesseract using that image. - Use multiple images like this one, build box files for each image and train tesseract using those files. Thank you for your help. -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en
