YAPPTCHA: Yet another picture promoted CAPTCHA with spam stopping, image labeling and SIFT accomplishment

Author

Babaei, Mehdi ; Ghoushchi, Mohammad B. Ghaznavi ; Noori, Abdollah

Author_Institution

Tehran Univ., Tehran, Iran

fYear

2013

fDate

14-16 May 2013

Firstpage

1

Lastpage

8

Abstract

We present YAPPTCHA, a new CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) as a security measure to recognize human users. The proposed system uses images instead of distorted text to label images as a valuable output. YAPPTCHA is generated from images on the Web. In order to solve this type of CAPTCHA, users must type two words for description of two images. When users pass the challenge, the provided meaningful labels are used to determine the content of images. In addition, semantic graphs for labels and images are created and it will make it possible to develop an image semantic search engine accordingly. Due to usage of images in this system, and its architecture, it is highly secure compared to its counterparts. In a user study involving 60 participants, YAPPTCHA´s word accuracy is measured to be 98.18% while 61.26% of attempts of the users were successful.

Keywords

graph theory; image retrieval; search engines; security of data; transforms; SIFT accomplishment; YAPPTCHA; completely automated public turing test to tell computers and humans apart; human user recognition; image labeling; image semantic search engine; security measure; semantic graphs; spam stopping; yet another picture promoted CAPTCHA; CAPTCHAs; Computers; Databases; Labeling; Security; Servers; Text recognition; CAPTCHA; Image labeling; Ontology; Security;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical Engineering (ICEE), 2013 21st Iranian Conference on

Conference_Location

Mashhad

Type

conf

DOI

10.1109/IranianCEE.2013.6599621

Filename

6599621