PiCAPTion: Picture CAPTCHAs for Internet Authentication
Apoorva RajendraAngre, Monal Dilip Kapadia, Meena Ugale
- Year
- 2015
- Citations
- 4
- Access
- Open access
Abstract
CAPTCHAs are tests that distinguish humans from software robots in an online environment. The most commonly encountered CAPTCHAs today take the form of a garbled string of words or characters. Unfortunately, existing text based CAPTCHAs suffer from several automated attacks. Thus, with the demonstration that character recognition CAPTCHAs are vulnerable to computer vision based attacks, this paper proposes alternatives to the traditional "Text based CAPTCHAs", in the form of "Image based CAPTCHAS", which require users to identify simple objects in the images presented, the argument is that object recognition is typically considered a more challenging problem than character recognition, due to the limited domain of characters and digits in the English alphabet.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002