Cross Entropy Clustering Approach to Iris Segmentation for Biometrics Purpose

Krzysztof Misztal,

Przemysław Spurek,

Emil Saeed,

Khalid Saeed,

Jacek Tabor

Abstrakt

This work presents the step by step tutorial for how to use cross entropy clustering for the iris segmentation. We present the detailed construction of a suitable Gaussian model which best fits for in the case of iris images, and this is the novelty of the proposal approach. The obtained results are promising, both pupil and iris are extracted properly and all the information necessary for human identification and verification can be extracted from the found parts of the iris.

Słowa kluczowe: CEC, cross entropy clustering, iris recognition, biometrics
References
[1] Daugman J., How iris recognition works. Circuits and Systems for Video Technology, IEEE Transactions on, 2004, 14(1), pp. 21–30.
[2] Tabor J., Spurek P., Cross-entropy clustering. Pattern Recognition, 2014, 47(9), pp. 3046–3059.
[3] Li P., Ma H., Iris recognition in non-ideal imaging conditions. Pattern Recognition Letters, 2012, 33(8), pp. 1012–1018.
[4] Ma L., Tan T., Wang Y., Zhang D., Efficient iris recognition by characterizing key local variations. Image Processing, IEEE Transactions on, 2004, 13(6), pp. 739–750.
[5] Misztal K., Saeed E., Tabor J., Saeed K., Iris pattern recognition with a new mathematical model to its rotation detection. In: Biometrics and Kansei Engineering. Springer, 2012, pp. 43–65.
[6] Freedman D., Statistical models: theory and practice. Cambridge University Press, Cambridge, United States of America, 2009.
[7] Misztal K., Tabor J., Mahalanobis distance-based algorithm for ellipse growing in iris preprocessing. In: Computer Information Systems and Industrial Management. vol. 8104. LNCS, Springer, London, 2013, pp. 158–167.

Czasopismo ukazuje się w sposób ciągły on-line.
Pierwotną formą czasopisma jest wersja elektroniczna.

Wersja papierowa czasopisma dostępna na www.wuj.pl