====== Enhance images for OCR ======

I use this code to enhance photographs or other image files taken from black and white text. Does great job for [[wp>optical character recognition]], printing and other purposes. This script is using [[http://www.imagemagick.org|ImageMagick]] to do the actual job.

<code bash>
#!/bin/bash

mkdir "bw"

for x in *.jpg ; do 
	b=`basename $x .jpg`
	echo $x
	convert -noise 1 -unsharp 10x5+10 -threshold 20% "$x" "bw/$b.pbm";
	unpaper "bw/$b.pbm" "bw/unpaper_$b.pbm"
	convert "bw/unpaper_$b.pbm" "bw/$b.png";
	rm -f "bw/$b.pbm" "bw/unpaper_$b.pbm"
done
</code>

{{tag>util convert imagemagick enhance image ocr bash}}

~~LINKBACK~~