>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".

Hmm, I think I agree with Dragan on this, that current OCR software may actually work better with grayscale than 1-bit black/white.

Have you tested yet? It would be fairly quick to do. You could start with a test image that only contains text, at the original colour depth. Then save it again as 1-bit black/white. See which gives the best results in OCR.

If you're starting with colour images, another thing to try might be to save as 8-bit grayscale.