>>Hi Al.
>>I'm using an OCR DLL to extract the text from an images.
>>The text in these images are always black. The black color is only used in the text part.
>>So, to improve the OCR results, I need to remove all non black pixels or change them to white, and save this "new image".
>
>
>I would suggest saving the image to a disk file, and manually manipulating it in a software program like GIMP to learn how to adjust it to your specifications, and then automating that process from the command line as per a script for future automated use.

And it goes without saying -- it's best to avoid image formats that are "lossy" or involve some sort of approximation when encoding -- especially if the text is small...
http://www.dkriesel.com/en/blog/2013/0802_xerox-workcentres_are_switching_written_numbers_when_scanning