Iris Feature Extraction and Matching Based on Space Pyramid

Abstract:

Iris feature extraction and classifier design are the key steps in iris recognition system, because it will directly affect the effect of iris recognition, especially for real-time iris recognition system, in order to extract enough information as possible while reducing the system Calculation, and find a balance between effectiveness and efficiency in the identification. the current proposed Gobor Dougman filtering is the main feature extraction. However, in the kinds of embedded systems, Gobor function need large amount of calculation, so this chapter put the pyramid matching classification in scenes into feature extraction, established a new model of feature extraction and recognition. The match effect is ideal in after large number of tests

• Periodical: Advanced Materials Research (Volume 459)
• Pages: 7-11
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.459.7
• Online since: January 2012
• Authors: Wei Peng, Qun Ying Yang, Song Gu
• Keywords: Component, Feature Extraction, Iris Recognition, Iris Segmentation, On Space Pyramid, Pyramid Kernel

References

[1] MA L., TAN T., WANG Y.: Personal identification based on iris texture analysis [J]. IEEE TRANS. Pattern Analysis and Machine Intelligence, 2003, 25 (12): 1519-1533.

DOI: 10.1109/tpami.2003.1251145

[2] PAN L., XIE M., MA Z. Iris localization based on multi-resolution analysis: International Conf. on Pattern Recognition [C]. (2008).

DOI: 10.1109/icpr.2008.4761844

[3] HUANG J., WANG Y., TAN T. A new iris segmentation method for recognition: International Conf. on Pattern Recognition [C]. 2004: 554—557.

[4] MA L., TAN T., WANG Y.: Efficient iris recognition by characterizing key local variations [J]. IEEE TRANS. Image Processing, 2004, 13 (6): 739—750.

DOI: 10.1109/tip.2004.827237

[5] BOLE W., BOASHASH B.: A human identification technique using images of the iris and wavelet transform [J]. IEEE Tran. on Signal Processing, 1998, 46 (4): 1185—1188.

DOI: 10.1109/78.668573

[6] PASSI A., KUMAR A. Improving iris identification using user quality and cohort information: IEEE Conf. on CVPR [C]. (2007).

DOI: 10.1109/cvpr.2007.383389

[7] DAUGMAN, J.: High confidence visual recognition of persons by a test of statistical independence [J]. IEEE TRANS. Pattern Analysis and Machine Intelligence, 1993, 15 (11): 1148—1161.

DOI: 10.1109/34.244676

[8] R. P. WILDES., Iris recognition: an emerging biometric technology, Proc. IEEE, vol. 85 1997 1348 - 1363.

DOI: 10.1109/5.628669

[9] MA Z., ZHENG T., PAN L. Classification-based algorithms for iris outer edge location: IEEE Conf. on ICCCAS [C]. 2009 493—496.

[10] LAZEBNIK S, SCHMID C., Ponce J. Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories: IEEE Conf. on CVPR [C]. (2006).

DOI: 10.1109/cvpr.2006.68

[11] OZUYSAL M., FUA P., LEPETIT V. Fast keypoint recognition in ten lines of code: IEEE Conf. on CVPR [C]. (2007).

DOI: 10.1109/cvpr.2007.383123

[12] OZUYSAL M., CALONDER M., LEPETIT V.: Fast keypoint recognition using random ferns. IEEE TRANS. Pattern Analysis and Machine Intelligence, 2010, 32 (3): 448—461.

DOI: 10.1109/tpami.2009.23