A Kind of De-noising and Segmentation Method for CAPTCHA with Colored Interference Lines

DOI

10.2991/icmmcce-15.2015.271How to use a DOI?

Keywords

CAPTCHA Recognition; Colored Interference Lines; Characters Segmentation

Abstract

The research of CAPTCHA recognition can discover the security vulnerabilities of CAPTCHA in time. It has great significance in improving the CAPTCHA design method and promoting the design level of CAPTCHA. Text-based CAPTCHA recognition mostly uses the method of characters segmentation and recognition. It is not very ideal for the CAPTCHAs containing colored interference lines, characters adhesion, rotation, distortion and scaling interference. A kind of de-noising and segmentation algorithm which is suited to the CAPTCHA with colored interference lines is presented in this paper. Finally, it is verified through a large number of real data.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Wang Zhao
AU  - Zitong Cheng
PY  - 2015/12
DA  - 2015/12
TI  - A Kind of De-noising and Segmentation Method for CAPTCHA with Colored Interference Lines
BT  - Proceedings of the 4th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering 2015
PB  - Atlantis Press
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmcce-15.2015.271
DO  - 10.2991/icmmcce-15.2015.271
ID  - Zhao2015/12
ER  -