On 30 June 2010 19:00, Professional Developer <[email protected]> wrote: > Hi, > > I created a project which accept an image file and then processed > using tessnet and then show the text of the image in a text box. But > its output is not 100% accurate. >
OCR, in general, is not 100% accurate. In controlled conditions, you may be able to approach 100%, but you shouldn't rely on it. As a rule of thumb, if a computer is being used for any sort of recognition task - speech recognition, face detection, face recognition, OCR - expect that there will always be a margin of error. > As far I know tessnet2 is a .net wrapper for tesseract-ocr and the > site http://www.free-ocr.com also used tesseract-ocr to process > images. But the output of http://www.free-ocr.com/ is 100% accurate > where tessnet2 is giving wrong text output for some of the images I > tested. Can you please let me know why tessnet2 is not working > properly? free-ocr.com uses Tesseract 3 which includes many improvements over Tesseract 2, which is used by Tessnet2. I have no idea of future plans with Tessnet2 - there's is a problem with Tesseract 3 on Windows that would have to be fixed first - but this is not a forum for Tessnet2. > > Thanks for your help in advance! > > Kind regards > > Altaf > > -- > 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. > > -- <Leftmost> jimregan, that's because deep inside you, you are evil. <Leftmost> Also not-so-deep inside 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.
