Hello, I use tesseract in my job, we work for a company that works in the invoice/commercial document recognition industry, we also work with Pegasus and Scansoft (two of the best commercial OCR engine), and I can tell you, that tesseract work as well as the other two for the majority of the jobs, In general Pegasus only outperforms tesseract in very poor images & dot matrix, and Scansoft in his dictionaries and his powerful layout recognition, me favourite is tesseract, because I've learned an invaluable lot of things with it and with the leptonica library, (I'm very grateful with the authors and the comunity that support this projects), and allows us to distribute a non-commercial version of one of our Scanning/Data entry programs with a nice an powerful OCR on it (tesseract of course) (take a look at www.chronoscan.org if you want), (you can't do this with commercial libraries).
Test your documents, and make a few statistics of performance, with tesseract you may do everything you want (with the commercial's one only what they do), but you will need to study and solve a lot of thing's by yourself, Make your balance and don't forget to comment your decision!! -- -- 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/groups/opt_out.
