Friday, January 8, 2010

Tesseract

To use Tesseract, you need an uncompress Tiff file. To do that:

C:\tools\ImageMagick-6.5.8\VisualMagick\bin\convert.exe c:\tmp4\toto.jpg c:\tmp4\toto.tif
C:\tools\Tesseract>tiffcp -c none c:\tmp4\toto.tif c:\tmp4\unc_toto.tiff
C:\tools\Tesseract>tesseract c:\tmp4\unc_toto.tif out

Go and read the OCR result in out.txt