Excuse me I changed some part of project and I forgot to re-upload zip file! we uploaded it as online tool in [1] also I repaired link [2] for offline works
[1] http://reza1615.github.com/index.html [2] https://github.com/reza1615/PersianOcr/blob/master/BoxMaker-en.zip<https://github.com/reza1615/PersianOcr/blob/master/BoxMaker-en.zip> On Wednesday, October 31, 2012 11:29:46 PM UTC+1, zdenop wrote: > > On Wed, Oct 31, 2012 at 10:42 AM, Reza M <[email protected] <javascript:> > > wrote: > >> Hi, >> In PersianOcr project <https://github.com/reza1615/PersianOcr> we >> developed a tool by php & JavaScript that can make a huge box in few >> Minutes! without printing and scan texts >> > > > *How it works?* >> It is a html tool that runs with browsers you should type or copy a text >> in input text box. >> it will create box and image that are used for trainingdata training. >> it works with all of browsers but we suggest you for texts more than >> 13000 you should use Firefox because the other browsers will crash! >> *Note*:IE 9 is very slow don't use it! >> >> *Huge Text* >> Till 10000 words Chrome and firefox will create image from text but more >> that it you should use Firefox and it's screenshot extension (Awesome >> screenshot:Capture and annotate 2.3.7) after capturing screen you can crop >> image according to rectangle. >> *Note*:chrome for more than 10k words will crash (tested for Persian) >> >> *Calibrating* >> Unfortunately Chrome and Firefox doesn't have the same result (box file) >> on the same system! after making box you should create similar box with >> tesseract-ocr >> (it is not importnet that is supporting your language or not. only write* >> **tesseract example.tif example -l eng batch.nochop makebox* ) and you >> should compaire the same character's numbers (i.e. you can add $$$ at the >> first line of your text to finding similar characters) >> you can use shift 1 , shift 2, shift 3, shift 4 text box for shifting all >> the boxes coordination for calibrating total boxes with image after >> pressing *UPDATE* your box will be prepared and you can use it. >> >> *Options >> *you can create box and image fore different languages (Right to left, >> Left to right, connected characters, compact texts, ZWNJ characters, >> Different fonts)* >> * >> *Fonts* >> By changing line 22 in default.html file you can add you font >> *That's it!* >> >> You can find this tool >> here<https://github.com/reza1615/PersianOcr/blob/master/BoxMaker-en.zip> >> >> Your link[1] does not work: 404 error. Please upload your program to > download section of your project. > > [1] https://github.com/reza1615/PersianOcr/blob/master/BoxMaker-en.zip > [1] https://github.com/reza1615/PersianOcr/downloads > > p.s.*To Admins*: is it possible to add this tool to wiki's training >> part? or add in part? >> your, >> Reza >> >> > -- > Zdenko > -- 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
