I have also tried different PSMs, but the results are not very promising. Correct for this image, but incorrect for other images. Hope you all can help me improve the accuracy. Thank you all. Vào lúc 19:41:44 UTC+7 ngày Thứ Ba, 26 tháng 3, 2024, inKi Wang đã viết:
> Hi everyone, I wish you all a good day. > > I'm currently encountering an issue with image_to_string producing > incorrect results when reading large gray images containing only numbers. > Here's what I'm using: > > - pytesseract version 0.3.10 > - tesseractOCR version 5.3.3 > - Language: English (eng) > - PSM: 7 > - OEM: 3 > > With the image provided below, the result returned when using the > image_to_string function is 9.5. When I resize the image, it returns 9.0, > 9.5, and sometimes *9.9*. There was an instance where resizing gave 5.5, > but it was incorrect for other cases with different numbers. > > Do you have any suggestions for me to improve the accuracy of the results? > Thank you all, and I wish you a great day! > > [image: 9.0.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 tesseract-ocr+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/3feac96b-98c0-4ae7-9dc6-e5a72485dfa0n%40googlegroups.com.
