Efficient Fingervein Sample Image Encryption

Sanjay Shekhawat; Heinz Hofbauer; Bernhard Prommegger; Andreas Uhl

Efficient Fingervein Sample Image Encryption

Sanjay Shekhawat^*, Heinz Hofbauer, Bernhard Prommegger, Andreas Uhl

^*Corresponding author for this work

Artificial Intelligence and Human Interfaces

Research output: Chapter in Book/Report/Conference proceeding/Legal commentary › Conference contribution › peer-review

Abstract

Efficient sample encryption techniques are investigated for fingervein data. We propose an approach where it suffices to encrypt 0.5% of the sample JPEG2000 bitstream and thereby completely disable biometric recognition. Evaluations
with 5 different recognition schemes on two different datasets reveal that results are stable accross all techniques considered as long as the start of the bitstream is encrypted.

Original language	English
Title of host publication	Proceedings of the 8th International Workshop on Biometrics and Forensics
Number of pages	6
Publication status	Published - Apr 2020

Fields of Science and Technology Classification 2012

102 Computer Sciences

Cite this

@inproceedings{e481b355ec35437b8eeb6931e555a7f0,

title = "Efficient Fingervein Sample Image Encryption",

abstract = "Efficient sample encryption techniques are investigated for fingervein data. We propose an approach where it suffices to encrypt 0.5% of the sample JPEG2000 bitstream and thereby completely disable biometric recognition. Evaluationswith 5 different recognition schemes on two different datasets reveal that results are stable accross all techniques considered as long as the start of the bitstream is encrypted. ",

author = "Sanjay Shekhawat and Heinz Hofbauer and Bernhard Prommegger and Andreas Uhl",

year = "2020",

month = apr,

language = "English",

booktitle = "Proceedings of the 8th International Workshop on Biometrics and Forensics",

}

TY - GEN

T1 - Efficient Fingervein Sample Image Encryption

AU - Shekhawat, Sanjay

AU - Hofbauer, Heinz

AU - Prommegger, Bernhard

AU - Uhl, Andreas

PY - 2020/4

Y1 - 2020/4

N2 - Efficient sample encryption techniques are investigated for fingervein data. We propose an approach where it suffices to encrypt 0.5% of the sample JPEG2000 bitstream and thereby completely disable biometric recognition. Evaluationswith 5 different recognition schemes on two different datasets reveal that results are stable accross all techniques considered as long as the start of the bitstream is encrypted.

AB - Efficient sample encryption techniques are investigated for fingervein data. We propose an approach where it suffices to encrypt 0.5% of the sample JPEG2000 bitstream and thereby completely disable biometric recognition. Evaluationswith 5 different recognition schemes on two different datasets reveal that results are stable accross all techniques considered as long as the start of the bitstream is encrypted.

M3 - Conference contribution

BT - Proceedings of the 8th International Workshop on Biometrics and Forensics

ER -