A Captcha Based on the Human Visual Systems Masking Characteristics

Author

Ferzli, Rony ; Bazzi, Rida ; Karam, Lina J.

Author_Institution

Dept. of Electr. Eng., Arizona State Univ., Tempe, AZ

fYear

2006

fDate

9-12 July 2006

Firstpage

517

Lastpage

520

Abstract

In this paper, a CAPTCHA is presented based on the masking characteristics of the human visual system (HVS). Knowing that noise can be masked by high activity regions and showing that edges can be masked by noise for a human observer while still being detected by machines, the suggested CAPTCHA is composed of English alphabets that are picked randomly and written with a combination of texture and edges with added noise such as to deceive the machine by randomly changing the visibility of characters for humans. The proposed CAPTCHA is highly legible and robust to brute-force attacks and sophisticated object character recognition (OCR) segmentation algorithms

Keywords

character recognition; image segmentation; object recognition; visual perception; CAPTCHA; English alphabets; HVS; OCR segmentation algorithm; human visual system; masking characteristics; object character recognition; Automatic testing; Character recognition; Computer science; Dictionaries; Humans; Noise robustness; Optical character recognition software; Search engines; Uniform resource locators; Visual system;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia and Expo, 2006 IEEE International Conference on

Conference_Location

Toronto, Ont.

Print_ISBN

1-4244-0366-7

Electronic_ISBN

1-4244-0367-7

Type

conf

DOI

10.1109/ICME.2006.262439

Filename

4036650