|
« Back
Captchas
Handwritten text offers challenges that are rarely encountered
in machine-printed text. In addition, most problems faced
in reading machine-printed text (e.g., character recognition,
word segmentation, letter segmentation, etc.) are more severe,
in handwritten text. In this project we explore the application
of Human Interactive Proofs (HIP), which is a relatively new
research area with the primary focus of defending online services
against abusive attacks. It uses a set of security protocols
based on automatic reverse Turing tests that humans can pass
but the state-of-the-art computer programs cannot. Failure
to pass the test suggests the evidence of artificial intelligence,
in machine form. This is accomplished by exploiting the differential
in the proficiency between humans and computers in reading
handwritten word images. We propose several methods to deform
handwritten text images to generate CAPTCHA challenges and
make them indecipherable by computers and explore Gestalt
psychology as a cognitive factor that assists humans in reading
and understanding. Experimental results on both humans and
computers are performed to show the existing gap, which could
be used as an excellent biometric for online security of Web
services.
Publications:
- A Human Interactive Proof Algorithm Using Handwriting Recognition, Amalia Rusu and Venu Govindaraju, Proc. 8th International Conference on Document Analysis and Recognition (ICDAR 2005)
- Visual CAPTCHA with Handwritten Image Analysis, Amalia Rusu and Venu Govindaraju, Proc. 2nd International Workshop on Human Interactive Proofs (HIP 2005), LNCS, Vol. 3517, 2005
- Challenges that handwritten text images pose to computers and new practical applications, Amalia Rusu and Venu Govindaraju. Proc. IS&T/SPIE 17th Annual Symposium Electronic Imaging Science and Technology, Conference on Document Recognition and Retrieval XII, SPIE Vol. 5676, pp. 84-91, 2005.
- Handwriting Word Recognition: A New CAPTCHA Challenge, Amalia Rusu and Venu Govindaraju. Proc. 5th International Conference on Knowledge Based Computer Systems, Allied Publishers Pvt. Ltd, pp. 347-357, 2004.
- Handwritten CAPTCHA: Using the Difference in the Abilities of Humans and Machines in Reading Handwritten Words, Amalia Rusu and Venu Govindaraju. Proc. 9th IAPR International Workshop on Frontiers of Handwriting Recognition (IWFHR 2004), IEEE Computer Society, ISBN 0-7695-2187-8, pp. 226-231, 2004.
|
|
 Fingerprint scan is the most widely deployed biometric.
|
