Removing handwriting from printed documents

asked 2014-08-01 08:52:09 -0500

I'm working on a project to automatically process scanned documents. These documents contain handwriting over printed character that damages the OCR accuracy. It can appear as a signature over a name and job title. These handwritings are more rounded and thin than the printed background and easily recognizable by human reading, but they do not differ by color or any easy image process that I could think of.

A similar issue was discussed here but with no hint for a solution -

I was wondering if any has had experience with detecting and removing these handwriting blocks out of a printed document.

Thanks in advance, Manuel

edit retag flag offensive close merge delete