Improving Compressed Iris Recognition Accuracy Using JPEG2000 RoI Coding

Abstract

The impact of using JPEG2000 region of interest coding on the matching accuracy of iris recognition systems is investigated. In particular, we compare the matching scores as obtained by a concrete recognition system when using JPEG2000 compression of rectilinear iris images with and without region of interest coding enabled. The region of interest is restricted to the iris texture area plus the pupil region. It turns out that average matching scores can be improved and that the number of false negative matches is significantly decreased using region of interest coding as compared to plain JPEG2000 compression.

Effects of severe image compression on iris segmentation performance

“…JPEG-XR is found to be competitive to the current standard JPEG 2000 while exhibiting significantly lower computational demands. For JPEG 2000, Hämmerle et al show that JPEG 2000 Part 2 can improve recognition accuracy by employing adapted wavelet packet basis instead of the fixed dyadic Part 1 decomposition [9] and also, JPEG 2000 region-of-interest coding is shown to by beneficial by assigning a higher bitrate to iristexture regions in the image [10].…”

Iris-Biometric Fuzzy Commitment Schemes under Image Compression

“…For the latter case, [4,6,9,17] are early works covering an assessment on recognition accuracy for standard approaches covering different IREX formats (K3 for compression of cropped iris images, K7 for ROI-masked and cropped images, K16 referring to unsegmented polar format). In [7,12,13] methods to adapt compression techniques (customizing quantization tables, ROI-coding) for advanced iris recognition are examined. The attention of most techniques is focused on lossy compression, since bit-rate savings are more significant as compared to lossless techniques.…”

Effects of JPEG XR Compression Settings on Iris Recognition Systems

“…Superior compression performance of JPEG2000 over JPEG is seen especially for low bitrates (thus confirming the choice of the above-referenced standards), however, for high and medium quality JPEG is found still to be competitive in terms of impacting recognition accuracy. Apart from applying the respective algorithms with their default settings and standard configurations, work has been done to optimise the compression algorithms to the application domain: For JPEG2000, we have proposed to invoke RoI coding for the iris texture area [3] whereas the removal of the image background before compression has also been suggested (i.e. parts of the image not being part of the eye like eye-lids are replaced by constant average gray [1]).…”