On 20 July 2015 at 20:40, Tom Morris <[email protected]> wrote: > Jeff's answer is probably the most important explanation, but some other > reasons include: > - Tess supports more languages > - Tess is older > - Tess has a bigger more well developed community (partly because of all the > other reasons) > - Tess is higher performance (from a resource utilization point of view, > last time I checked) > > Ocropus is/was pretty much a one-man project and was, as I understand it, > designed to support his research.
That seems to be true at the moment, but there were a few people working on it at different stages. > It also went through a significant > rewrite as a result of a change in implementation strategy and that > discontinuity probably didn't help things. Several rewrites. One of them was based around line-oriented FSTs, and interestingly enough, similar work was done with Tesseract (https://github.com/tesseract-ocr/tesseract/pull/29). The current version of OCRopus uses LSTM, which is one of the currently fashionable types of neural network. -- <Sefam> Are any of the mentors around? <jimregan> yes, they're the ones trolling you -- 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]. To post to this group, send email to [email protected]. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CAHh9-xs_i%3DR3j74LOaKjuKMs7rY_cC6-VuUeFYYW0fjLcFpxPw%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
