> > Dear TrueWodzu, > Use file datatrain best for digits https://github.com/Shreeshrii/tessdata_shreetest/blob/master/digits.traineddata And before you set image to OCR by Tesseract, you can pre processing image, your image is low quality. You can use function Cv2.Erode() with size (5,5) and SetSetResolution(xDpi = 300, yDpi = 300) ( it's best to OCR) then use tesseract to OCR.
- This is image after process: [image: Capture.PNG] - Command: tesseract Capture.PNG output --psm 6 -l digits - Result: [image: result.PNG] -- 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 [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/490a4d77-4985-4165-a731-5bac45829257%40googlegroups.com.
