I can't get some of my docs with images to be recognized by OCR. They're not especially low-resolution — though some are distorted — but I can't get them through OCR even with Omnipage. I uploaded one as an example (converted from DOC to PDF for Omnipage) but I have more. What can I do to make OCR succeed?

| |

Despite how they look on the screen, the text images are not very high resolution. You can see this by magnifying the view in a pdf viewer. The images are pixelated and not all black and white.

I extracted the images with pdfimages. Gocr worked on the resulting .ppm images, but with many errors. I could not get tesseract to work with the images despite conversion to monochrome tiff.

| |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.