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.

Abstract:An iris recognition algorithm based on 1D spatial domain signatures is improved by extending template data from mean vectors to 2D histogram information. EER and shape of the FAR curve is clearly improved as compared to the original algorithm, while rotation invariance and the low computational demand is maintained. The employment of the proposed scheme remains limited to the similarity ranking scenario due to its overall FAR/FRR behaviour.