1. Human Based Character Recognition Via Web-Security Measures <br />Original Research By<br />Luis Von Ahn<br /> Benjamin Maurer<br /> Colin McMillen<br /> David Abraham<br /> Manuel Blum<br />Presented BY : <br />Md. ShihabUddin<br />Roll: 0607029, CSE,KUET <br />This paper was published in Science Express on 14 August 2008 by the American Association for the Advancement of Science (AAAS).<br />
10. CAPTCHA’S<br /><ul><li>A CAPTCHA(COMPLETELY AUTOMATED TURING TEST TO TELL COMPUTERS & HUMANS APART) is a program that can tell its user whether a human or computer.
11. Colorful images with distorted text at the bottom of web registration forms.
12. Only can be deciphered by humans, computer programs or autobot's can’t .</li></ul>Applications: <br /><ul><li>Free e-mail services, social networks,blogs
13. Data collection
14. Preventing worms & spam
15. Preventing dictionary attacks </li></li></ul><li>Why Re-inventing CAPTCHA <br />A calculation: <br /><ul><li>Time takes to solve a CAPTCHA= 10 seconds
16. Daily solved CAPTCHA’S= more than 200 millions
17. Human hours lost= more than 150,000 hours a day.
18. 6% of world’s population type’s CAPTCHA everyday</li></li></ul><li>Why Re-inventing CAPTCHA<br />Though CAPTCHA’S prevents spam’s & autobot’s but this human effort is totally wasted everyday.<br />Is there anyway to use this HUMAN effort for something good?<br />
19. Solution is: Re-CAPTCHAor Re-invented CAPTCHA <br />
20. Digitizing Books: Normal Approach<br />SCAN<br />O<br />C R<br />Problem is OCR is not perfect. <br />Cannot Decipher 20% of the word’s whereas Re-CAPTCHA can 99%<br />
21. Digitizing Books: Re-CAPTCHA Approach<br />WORD’s that OCR Cannot Read <br />SCANNED BOOK<br />Randomly Distorted Image of WORD <br />
22. Digitizing Books: Re-CAPTCHA Approach<br />Randomly Distorted Image of WORD <br />Added in Random Order <br />Known Distorted Control Word <br /> Re-CAPTCHA <br />
23. Digitizing Books: Re-CAPTCHA Approach<br /> Re-CATCHA <br /><ul><li>One Re-CAPTCHA is sent to many users.Same word typed by 3 users & matches with OCR Guess, word digitized
24. Skipped by 6 users to type Re-CAPTCHA,WordConsidered Un-readable </li></li></ul><li>Re-CAPTCHA IN USE <br />FREE TO USE <br /> Popular Users<br />Facebook<br />CraiglistMore than 100,000 Websites <br />Twitter<br />
25. Re-CAPTCHA IN USE <br />Re-CAPTCHA IN TWITTER <br />
26. Re-CAPTCHA IN USE <br />Re-CAPTCHA IN FACEBOOK<br />
27. Words Digitized Per Day <br />
28. Re-CAPTCHA IN USE <br />Digitization Rate:<br />4 Million Words Per Day<br />Approximately 160 Books(400 pages,250 words per page) Per Day<br />This ratio’s are very old, current rate is very high, cause Facebok+Twitter now have nearly 500 million users & using Re-CAPTCHA.<br />
29. Re-CAPTCHA IN USE <br /> Words are coming from:<br />The NEWYORK TIMES(1851-1980)<br />Internet Archive <br />Stored In:<br />Google News<br />Google Books<br />
30. Re-CAPTCHA CURRENT<br />GOOGLE Acquired Re-CAPTCHA <br />LUIS VON AHN works as Research Scientist at GOOGLE along with his job at Carnegie Mellon. <br />LUIS VON AHN’s co-workers who worked on Re-CAPTHA are now working on GOOGLE.<br />LUIS VON AHN awarded a lot for inventing CAPTCHA & Re-CAPTCHA including Mc Arthur Fellowship, One of The Best 10 Computer Scientist of the world, Pioneer of Human Computation.<br />
31. REFERENCES <br />Paper from www.sciencmag.org<br />http://www.captcha.net<br />http://www.re-captcha.net<br />http://www.captcha.net<br />http://www.cs.cmu.edu/~biglou Homepage of LUIS VON AHN<br />Pictures from Web: Facebook,Twitter,Google & other sites <br />