Comparison of compression algorithms' impact on Iris recognition accuracy

Authors:
Stefan Matschitsch;Martin Tschinder;Andreas Uhl
Affiliations:
School of Telematics & Network Engineering, Carinthia Tech Institute, Austria;School of Telematics & Network Engineering, Carinthia Tech Institute, Austria;School of Telematics & Network Engineering, Carinthia Tech Institute and Department of Computer Sciences, Salzburg University, Austria
Venue:
ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics
Year:
2007

Citing 6
Cited 4

Fractal image compression: theory and application

Fractal image compression: theory and application
JPEG 2000: Image Compression Fundamentals, Standards and Practice

JPEG 2000: Image Compression Fundamentals, Standards and Practice
JPEG Still Image Data Compression Standard

JPEG Still Image Data Compression Standard
Effects of JPEG and JPEG2000 compression on face recognition

ICAPR'05 Proceedings of the Third international conference on Pattern Recognition and Image Analysis - Volume Part II
A new, fast, and efficient image codec based on set partitioning in hierarchical trees

IEEE Transactions on Circuits and Systems for Video Technology
How iris recognition works

IEEE Transactions on Circuits and Systems for Video Technology

Face recognition in JPEG and JPEG2000 compressed domain

Image and Vision Computing
Custom Design of JPEG Quantisation Tables for Compressing Iris Polar Images to Improve Recognition Accuracy

ICB '09 Proceedings of the Third International Conference on Advances in Biometrics
Improving Compressed Iris Recognition Accuracy Using JPEG2000 RoI Coding

ICB '09 Proceedings of the Third International Conference on Advances in Biometrics
Effects of JPEG XR compression settings on iris recognition systems

CAIP'11 Proceedings of the 14th international conference on Computer analysis of images and patterns - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

The impact of using different lossy compression algorithms on the matching accuracy of iris recognition systems is investigated. In particular, we relate rate-distortion performance as measured in PSNR to the matching scores as obtained by a concrete recognition system. JPEG2000 and SPIHT are correctly predicted by PSNR to be well suited compression algorithms to be employed in iris recognition systems. Fractal compression is identified to be least suited for the use in the investigated recognition system, although PSNR suggests JPEG to deliver worse recognition results in the case of low bitrates. PRVQ compression performs surprisingly well given the third rank in PSNR performance, resulting in the best matching scores in one scenario. Overall, applying compression algorithms is found to increase FNMR but does not impact FMR. Consequently, compression does not decrease the security of iris recognition systems, but "only" reduces user convenience.