Robert Maas, <jaycx2.3.calrobert@spamgourmet.com.remove> wrote:
+---------------
| > From: p...@informatimago.com (Pascal J. Bourguignon)
| > I know no OCR able to do a good job on badly printed or badly
| > scanned pictures.
| 
| There ought to be such a beast. If not, I could write one if
| anybody was willing to pay me for my labor.
+---------------

Spammers are always willing to pay for technological advances
in this area, to defeat CAPTCHAs.

Oh, wait, they *did* that already!!  See:

    http://en.wikipedia.org/wiki/Captcha#Computer_character_recognition
    ...
    Several research projects have broken real world CAPTCHAs,
    including one of Yahoo's early CAPTCHAs called "EZ-Gimpy"[1]
    and the CAPTCHA used by popular sites such as Paypal [12],
    LiveJournal, phpBB, and other open source solutions [13] [14] [15].
    In January 2008 Network Security Research released their program
    for automated Yahoo! CAPTCHA recognition.[16] Windows Live Hotmail
    and Gmail, the other two major free email providers, were cracked
    shortly after.[17] [18]

    In February 2008 it was reported that spammers had achieved a
    success rate of 30% to 35%, using a bot, in responding to CAPTCHAs
    for Microsoft's Live Mail service [19] and a success rate of 20%
    against Google's Gmail CAPTCHA.[20] A Newcastle University research
    team has defeated the segmentation part of Microsoft's CAPTCHA
    with a 90% success rate, and claim that this could lead to a
    complete crack with a greater than 60% rate.[21]
    ...


-Rob

-----
Rob Warnock			<rpw3@rpw3.org>
627 26th Avenue			<URL:http://rpw3.org/>
San Mateo, CA 94403		(650)572-2607