Protecting biometric data for personal identification

Authors:
Muhammad Khurram Khan;Jiashu Zhang;Lei Tian
Affiliations:
Research Group for Biometrics (RGB), Sichuan Province Key Lab of Signal and Information Processing, Southwest Jiaotong University, Chengdu, Sichuan, P.R China;Research Group for Biometrics (RGB), Sichuan Province Key Lab of Signal and Information Processing, Southwest Jiaotong University, Chengdu, Sichuan, P.R China;Research Group for Biometrics (RGB), Sichuan Province Key Lab of Signal and Information Processing, Southwest Jiaotong University, Chengdu, Sichuan, P.R China
Venue:
SINOBIOMETRICS'04 Proceedings of the 5th Chinese conference on Advances in Biometric Person Authentication
Year:
2004

Citing 3
Cited 4

High Confidence Visual Recognition of Persons by a Test of Statistical Independence

IEEE Transactions on Pattern Analysis and Machine Intelligence
Secure hybrid robust watermarking resistant against tampering and copy attack

Signal Processing - Special section: Security of data hiding technologies
Hiding Biometric Data

IEEE Transactions on Pattern Analysis and Machine Intelligence

Multimodal biometric image watermarking using two-stage integrity verification

Signal Processing
Chaos and NDFT-based spread spectrum concealing of fingerprint-biometric data into audio signals

Digital Signal Processing
Securing biometric templates for reliable identity authentication

ICIC'05 Proceedings of the 2005 international conference on Advances in Intelligent Computing - Volume Part II
Robust hiding of fingerprint-biometric data into audio signals

ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new chaotic watermarking and steganography method to protect biometric data, which is sent over the networks for personal identification Unlike other methods, we utilized two keys, one for encrypting the biometric template before embedding, which makes our method more secure and another for watermark embedding that makes our method more robust The proposed method does not require original biometric image for the extraction of watermarked data, and can provide high accuracy of extracted watermarked data even under different noises and distortions Experimental results show that the performance of the proposed method is encouraging comparable with other methods found in the current literature and can be used in a practical system.