Telling computers and humans apart automatically using activity recognition

Author

Vimina, E.R. ; Areekal, Alba Urmese

Author_Institution

Dept. of Comput. Sci., Rajagiri Coll. of Social Sci., Kalamassery, India

fYear

2009

fDate

11-14 Oct. 2009

Firstpage

4906

Lastpage

4909

Abstract

This paper proposes a new image based CAPTCHA test, activity recognition CAPTCHA. In this test the user is presented with a set of distorted images depicting a randomly chosen activity. The user has to recognize the common activity associated with the images and annotate it from a given list of activities to pass the test. The user studies indicate that this CAPTCHA can be solved with 99.04% average pass rate while that of ESP PIX CAPTCHA is 85.44% and SQUIGL PIX is 67.84%. Average time taken to pass the test is less than 10 seconds.

Keywords

computer vision; graphical user interfaces; human computer interaction; image recognition; security of data; GUI; SQUIGL PIX; activity recognition; image based CAPTCHA test; image distortion; machine vision problem; Automatic testing; Computer science; Cybernetics; Educational institutions; Electrostatic precipitators; Humans; Image recognition; Internet; Text recognition; USA Councils; Activity recognition; CAPTCHA; reverse turing test; security;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 2009. SMC 2009. IEEE International Conference on

Conference_Location

San Antonio, TX

ISSN

1062-922X

Print_ISBN

978-1-4244-2793-2

Electronic_ISBN

1062-922X

Type

conf

DOI

10.1109/ICSMC.2009.5346260

Filename

5346260