Multi (split) image spam

[Jim Barber]

I don't know if it's possible or not, but perhaps these images could be stitched together into one large image before they are presented to FuzzyOCR.
That would probably take a bit of work as you'd need to know from the layout how to stitch the images together (side-by-side? top-to-bottom? 2x2, etc).
But once stitched and passed to FuzzyOCR it should then be able to extract complete words from the final image.

----------
Jim Barber
DDI Health


Gareth wrote:
> Does anyone have an example of one of these spams?
> 
> I was thinking it should be possible to write a rule to detect these as
> there is no real reason why two images should be directly next to each
> other.
>