Hi Nick, Thank you for your knowledgeable response.
" but note that Tesseract isn't designed for handwriting, so the results are unlikely to be particularly good.", my primary motive for OCR is to extract text from scanned handwriting material, when Tesseract was recommended to me, I thought the individual meant to include handwriting as well, so, now I guess I'll have to look at other option. Nevertheless, I appreciate your input and thoughts. Don On Tuesday, March 25, 2014 10:32:21 AM UTC-4, Nick White wrote: > > Hi Don, > > Yes, you sound like you understand. I'll answer more below. > > > Sample text file(s), turn them into tiff images, each image > > represent a font? > > (max 64 of them) Then, we have box files as well. What's the > relationship > > between image files and box files? > > Box files state the coordinates of each character in an image. > > > Editing each box file seems not only > > time-consuming but error-prone, so, jTessBoxEditor seems a good tool to > use. > > Yes, agreed. Though if you just generate the images directly from a > sample text file, the appropriate box files should be automatically > generated (I presume jTessBoxEditor does this, but haven't used it > myself.) > > > Also, how about handwriting files as sample files (which have > > been scanned as image > > files)? And can jTessBoxEditor be used for these sample files as well? > > This could work, and the process would be the same, but note that > Tesseract isn't designed for handwriting, so the results are > unlikely to be particularly good. Handwriting doesn't tend to be as > regular as printed text, so there are different things to consider > there. There are probably different projects you can find that > should handle this better. > > Hopefully everything is a bit more clear for you now. Do ask more if > you need to! > > Nick > -- -- 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/d/optout.
