[FoRK] image processing for OCR

Eugen Leitl < eugen at leitl.org > on > Mon Jul 3 08:19:11 PDT 2006

On Mon, Jul 03, 2006 at 10:08:22AM -0500, Ken Meltsner wrote:

> Back in my metallography days, we would use various monochrome
> algorithms.  You'd "grow" an outline by adding black at the corners
> and such to fill in gaps, and then you could shrink back to remove the
> extra pixels not at corners.  Goal was exactly as you describe --
> filling in outlines, connecting broken structures, etc.

I did try dilate/erode, but it punches holes into letters
(or fuses letters, if used too heavily). I'm playing with
several parameters in Gimp right now, and while it does improve
things for the human eye I'm not yet sure about OmniPro 15
(I don't have access to 14, to see whether the OCR engine
recognition quality was degraded).
> It's been more than a decade since I worked in this area, so I can't
> remember much past these scant details.  Look for quantitative image
> analysis, I guess.

There is definitely a www cliff. What went before could as well
be not there.

Eugen* Leitl <a href="http://leitl.org">leitl</a> http://leitl.org
ICBM: 48.07100, 11.36820            http://www.ativel.com
8B29F6BE: 099D 78BA 2FD3 B014 B08A  7779 75B0 2443 8B29 F6BE

More information about the FoRK mailing list