I agree with you, but the boss wants ocr.. I think i will leave hime to figure is out I have to much coding to do .. lol ...<br><br>thanks for the input .. have a grate day ..<br><br><div><span class="gmail_quote">On 1/13/06,
<b class="gmail_sendername">Bill Rugolsky Jr.</b> <<a href="mailto:brugolsky@telemetry-investments.com">brugolsky@telemetry-investments.com</a>> wrote:</span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
On Fri, Jan 13, 2006 at 10:47:02AM +0000, Paul F. Johnson wrote:<br>> Grab a copy of gocr, compile and install (it's not in FE which is odd).<br>> When you scan, ensure it's at as high a resolution as possible (minimum
<br>> in my experience of 300 dpi) and grey scaled.<br>><br>> Use either gimp or xsane to grab the scan and tell gocr to do it's<br>> business.<br>><br>> OCR is not an exact science and you will really need to sit down and go
<br>> through the scanned text to ensure that the numbers scanned are correct<br>> (very easy to spot, you may have @ instead of 0, l for 1 and the such).<br>> Save the file generated. You may then need to either write a script to
<br>> delimit using " " as the target or feed it into emacs and then search<br>> and replace " " for "," - save.<br><br>Sadly, in my (limited) experience, none of the free software solutions
<br>such as Gocr or Clara OCR is really up to the task. The leading<br>proprietary packages are vastly superior. Some of them have free 30-day<br>evaluations.<br><br>With a proper setup for lots of automated training, Clara might be able
<br>to do the job. Especially if you do some image morphology (using, e.g.,<br>GIMP) to clean up the scans. But you'll have to do some serious work.<br><br>A tried and true technique that avoids using proprietary software
<br>is to simply pay multiple people to type the whole thing, and then<br>reconcile the differences (or use majority voting). :-)<br><br>Regards,<br><br> Bill Rugolsky<br></blockquote></div><br><br clear="all"><br>
-- <br>Gregory Machin<br><a href="mailto:greg@linuxpro.co.za">greg@linuxpro.co.za</a><br><a href="mailto:gregory.machin@gmail.com">gregory.machin@gmail.com</a><br><a href="http://www.linuxpro.co.za">www.linuxpro.co.za</a>
<br><a href="http://www.exponent.co.za">www.exponent.co.za</a><br>Web Hosting Solutions<br>Scalable Linux Solutions <br><a href="http://www.iberry.info">www.iberry.info</a> (support and admin)<br><br>+27 72 524 8096