Re: Franken+ Released -- New Tool For Training Tesseract on Fonts from Page Images

Dear all, Thanks to Matt and Bryan for making me aware of this interesting discussion! My name is Clemens Neudecker and I have been the Technical Manager of the IMPACT project (www.impact-project.eu). Without going into greater detail about the points that have already been discussed at

Re: Franken+ Released -- New Tool For Training Tesseract on Fonts from Page Images

Hi Bryan, On Tue, Dec 10, 2013 at 07:18:57PM -0600, Bryan Tarpley wrote: We've found that when two letters aren't touching, Tesseract has trouble identifying them together as a single ligature, /especially/ given that the character e by itself looks exactly the same as the one in ke. Oh,

Re: Franken+ Released -- New Tool For Training Tesseract on Fonts from Page Images

Dear Clemens, There's lots of great stuff in your email, thanks so much for sending it! It'll take me a while to get through; I'm likely to reply again later on. I just took a look at the ocrevalUAtion tool, and read the pages at https://sites.google.com/site/textdigitisation/ - it looks very

Re: Franken+ Released -- New Tool For Training Tesseract on Fonts from Page Images

Hi Nick, Thanks for the encouraging reply, looking forward to further feedback and comments! I think the main distinction the https://sites.google.com/site/textdigitisation/ OCR list was trying to make is between online (web-based) services and stand-alone tools, but I will point out to the