That isn't a brightness issue at all. It's just that the characters look too similar, so the OCR software guesses wrong. It seems that there isn't a solution for that problem other than editing. I wonder if some software has been designed to do the same thing with OCR as with voice recognition, so the user could "train" the software to recognize certain shapes as a different character than might be expected. That would sometimes be useful, but of course it wouldn't be too helpful when it isn't possible to see the character being misrecognized. It would still have problems sometimes anyway, because i's and 1's can be recognized incorrectly and correctly in the same document. Sarah Van Oosterwijck http://home.earthlink.net/~netentity/ ----- Original Message ----- From: "Pam Quinn" <quinns@xxxxxxxxxxxxx> To: <bksvol-discuss@xxxxxxxxxxxxx> Sent: Friday, December 03, 2004 6:24 PM Subject: [bksvol-discuss] what about letters for numbers > If page numbers have l for 1, i for 1, o for 0, etc., is this an > indicator that brightness should be turned up or down? > > Pam > > >