Hi, I have compiled and tested tesseract. IMHO it is better than gocr and ocrad, but it is finniky about the images it handles. It does not just ocr any tif file. It has to be at specific resollution and things like that. There is a script that prepare the image to work. With image magic one can convert whatever into the required .tif. I had a funny experience with this program on my fedora 3 box. It compiled, but hung when I ran it. Under Debian, it worked. I suspect some gcc version issue. It is good news in general, and if I had to do a lot of OCR now, I would have used it as is. I would say it is about like the old easy scan stuff from Arcenstone. It is also rather slow. Regards, Willem On Thu, 28 Sep 2006, Michael Whapples wrote: > By the way the URL you gave is wrong, www.sf.net/projects/tesseract-ocr > > From > Michael Whapples > ----- Original Message ----- > From: "Lorenzo Taylor" <lorenzo at taylor.homelinux.net> > To: "speakup" <speakup at braille.uwo.ca> > Sent: Thursday, September 28, 2006 10:04 PM > Subject: OCR on Linux: great news > > > > -----BEGIN PGP SIGNED MESSAGE----- > > Hash: SHA1 > > > > I just read a review on linux.com about a new open source OCR engine for > > Linux. Well, it's not exactly new, but it has recently been open > > sourced by none other than Google, HP and UNLV. According to the > > review, it's about 97.74% accurate, although it only recognizes tif files > > and doesn't yet correctly understand page layouts with more than 1 > > column. However these are planned features in future releases. This > > app is called tesseract, and can be found at > > > > http://sourceforge.net/projects/tesseract > > > > HTH somebody, > > Lorenzo > > - -- > > I've always found anomalies to be very relaxing. It's a curse. > > - --Jadzia Dax: Star Trek Deep Space Nine (The Assignment) > > -----BEGIN PGP SIGNATURE----- > > Version: GnuPG v1.4.5 (GNU/Linux) > > > > iD8DBQFFHDjUG9IpekrhBfIRAq5PAKDFpBdtnH/47VOxAs9K0ow7HbxtjgCeOgGp > > 1ORpTF+O/MpkioCwRBLFn28= > > =Kxdp > > -----END PGP SIGNATURE----- > > > > > > > > _______________________________________________ > Speakup mailing list > Speakup at braille.uwo.ca > http://speech.braille.uwo.ca/mailman/listinfo/speakup > -- This message is subject to the CSIR's copyright, terms and conditions and e-mail legal notice. Views expressed herein do not necessarily represent the views of the CSIR. CSIR E-mail Legal Notice http://mail.csir.co.za/CSIR_eMail_Legal_Notice.html CSIR Copyright, Terms and Conditions http://mail.csir.co.za/CSIR_Copyright.html For electronic copies of the CSIR Copyright, Terms and Conditions and the CSIR Legal Notice send a blank message with REQUEST LEGAL in the subject line to CallCentre at csir.co.za. This message has been scanned for viruses and dangerous content by MailScanner, and is believed to be clean. MailScanner thanks Transtec Computers for their support.
