I'm using everything as provided in the download. I was able to get some success by enlarging the image a bit when I cropped and converted it from PDF to TIF, but it still occurs on other images.
On Tuesday, January 28, 2025 at 1:41:35 AM UTC-5 sara.el...@gmail.com wrote: > I'm also facing the same problem. > - Which model are you using? > - Is it from the original tessdata models or a new one you tuned? > - Also, is the original model from the tessdata folder, or from the > tessdata/scripts folder? > > On Mon, Jan 27, 2025 at 5:56 PM Farokh Irani <bts.f...@gmail.com> wrote: > >> I have a small .TIF file with only around 28 characters. It's 300 DPI, >> B&W, no compression. >> The issue is that in the image I have the following text: >> 04-50288 2 and after OCR, I wind up with the text 0464-502882. >> I've tried using different --psm (6, 7, 11, 13), all produce the same >> output. >> >> Any ideas on how I can fix this? >> >> Thanks! >> >> -- >> 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-oc...@googlegroups.com. >> To view this discussion visit >> https://groups.google.com/d/msgid/tesseract-ocr/62160493-9777-4a90-8450-7632bbaf3a80n%40googlegroups.com >> >> <https://groups.google.com/d/msgid/tesseract-ocr/62160493-9777-4a90-8450-7632bbaf3a80n%40googlegroups.com?utm_medium=email&utm_source=footer> >> . >> > -- 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 visit https://groups.google.com/d/msgid/tesseract-ocr/69f54aaa-2533-40be-9280-04e7a8fa5b9dn%40googlegroups.com.
