Abstract— The impact of using (adaptive) wavelet packet subband structures as allowed in JPEG2000 Part 2 in iris image compression is investigated. The recognition performance of four different feature extraction schemes applied to correspondingly compressed images is compared to the usage of the dyadic decomposition structure of JPEG2000 Part 1 in the compression stage. A better recognition performance of the adaptively generated wavelet subband structures is observed, in particular of those generated with respect to optimal rate-distortion performance.
Index Terms— JPEG2000, wavelet packets, iris recognition, IREX.
J. Hämmerle-Uhl was with University of Salzburg, Austria. She is now with e-mundo Inc, Austria (e-mail: jhaemm@cosy.sbg.ac.at). E. Tillian is with the University of Salzburg, Austria (e-mail: Ernst.Tillian@stud.sbg.ac.at). A. Uhl is with the Computer Sciences Department, University of Salzburg, Austria (e-mail: andreas.uhl@sbg.ac.at).
[PDF]
Cite: Jutta Hämmerle-Uhl, Ernst Tillian, and Andreas Uhl, " Recognition Impact of JPEG2000 Part 2 Wavelet Packet Subband Structures in IREX K3 Iris Image Compression," International Journal of Information and Electronics Engineering vol. 5, no. 1, pp. 51-54, 2015.