Hi, I'm trying to OCR my gas meter [1] usage, and I stumbled upon issue that tesseract doesn't recognize anything in some tif images, just gives "empty page".
Has anybody had this issue? Here are cropped numbers: https://dl.dropbox.com/u/184632/ocr-gas-cropped.tif $ tesseract ocr-gas-cropped.tif output Tesseract Open Source OCR Engine with LibTiff Empty page as you can see it just fails to recognize, so I GIMPed the image and got this one: https://dl.dropbox.com/u/184632/ocr-gas-cropped-grayscale.tif and that one works: $ tesseract ocr-gas-cropped-grayscale.tif output Tesseract Open Source OCR Engine with LibTiff $ cat output.txt O 1 5 1 1@3» »'4*?5 But when I went one step further and cleaned the image to be more easily scanned it fails again: https://dl.dropbox.com/u/184632/ocr-gas-cropped-grayscale-clean.tif $ tesseract ocr-gas-cropped-grayscale-clean.tif output Tesseract Open Source OCR Engine with LibTiff Empty page Any ideas why is this happening? If possible I would like to use tesseract for automatically reading my gas meter usage, is this even possible? Is it possible to force tesseract to recognize only numbers and to ignore letters? [1] https://dl.dropbox.com/u/184632/ocr-gas-meter.jpg Cheers, Valent. -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en
