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.