Hello- I've downloaded and compiled the source for Tesseract 3.02.02 and installed the English learning files. To test the installation I am using what I believe to be a pristine input image which was just a screenshot of some tesseract home page text- so there is no markings or anything like that which may occur from a scanned text image. I fed this image into tesseract but the output is mostly garbled and the conversion very poor. A couple of words were correctly translated but the rest is not close. I have a feeling that something may be off in my environment or something and someone might see the output and know immediately what my issue is.
I'm running on a 64 bit Linux RedHat 6 install. Initially I built and installed tesseract 3.03 but had the same result. So I ran 'sudo make uninstall' and then compiled and installed 3.02 instead but there was very little difference in the output. I confirmed that english language was installed with: > tesseract --list-langs List of available languages (1): eng I've attached the input image as well as the file containing the output text. Is this output what I should expect, or is something definitely off here? Any assistance that folks could give would be greatly appreciated! Thank you. -- -- 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 --- 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 [email protected]. For more options, visit https://groups.google.com/d/optout.
Tessevacl dues vanuus Image pmcesslng upevalluns Internally (using me Leplunlca library) befuve dulng me actual OCR. It generally dues a very guud jub uflhls, bullheve wm inevitably be cases where :1 Isn‘I guud encugn, much can result m a significant reduction m accuracy.
<<attachment: Screenshot.png>>
