Two-factor face authentication using matrix permutation transformation and a user password

Jeonil Kang, Daehun Nyang, Kyunghee Lee

Research output: Contribution to journalArticlepeer-review

35 Scopus citations


Although authentication using biometric techniques is convenient, security issues such as the loss of personal bio-information are serious problems. However, the development of a secure biometrics scheme poses considerable challenges because users' bio-information is not precisely the same for each authentication attempt. This uncertainty during the authentication process obstructs direct application of cryptographic one-way functions in the authentication system. In this paper, we suggest a two-factor face authentication scheme using matrix transformations and a user password. Our scheme is designed with a secure cancellation feature, in that templates composed of permutation and feature vectors can be freely changed. Through experimental scenarios and results, we introduce the notable features of our scheme. Furthermore, we consider possible attacks on the proposed scheme and suggest security enhancement methods.

Original languageEnglish
Pages (from-to)1-20
Number of pages20
JournalInformation Sciences
StatePublished - 10 Jun 2014

Bibliographical note

Funding Information:
Portions of the research in this paper use the FERET database of facial images collected under the FERET program, sponsored by the DOD Counterdrug Technology Development Program Office.

Funding Information:
This work was supported by Inha University, Republic of Korea.


  • Biometrics security
  • Face authentication
  • User privacy


Dive into the research topics of 'Two-factor face authentication using matrix permutation transformation and a user password'. Together they form a unique fingerprint.

Cite this