I finally got this working, though my solution was to try larger files, and to repeat the training instructions a few more times until they worked. Not sure exactly where my error was originally, but it's working now.
On Feb 11, 1:31 pm, Michael Lissner <[email protected]> wrote: > Hi, > > I'm trying to teach Tesseract to understand blackletter fonts, but it > seems like I'm missing a critical step. I've followed the training > document, and even wrote up the process on my blog[1], but after I'm > done, the quality is identical to it was before I ran the training. > > It almost seems like I'm not using the training data that I'm > generating, but I *am* copying it to /usr/local/share/tessdata, and > then running tesseract with the correct language (eng). > > Is there a step I'm missing that tells Tesseract to **use** the files > I'm generating? Or is there something missing from my process that I > wrote up? > > Would *really* love some help with this - I've been trying to add > these fonts for a couple weeks now with no real progress, and I'm > beginning to lose hope. I really do need these to work though. > > Thanks, > > Mike > > [1]:http://michaeljaylissner.com/blog/adding-new-fonts-to-tesseract-3-ocr... -- 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
