Finger-Knuckle-Print Recognition Using Local Orientation Feature Based on Steerable Filter
Automatic personal identification based on finger-knuckle-print (FKP) has been considered as a promising technology in biometrics family in recent years. Previous work indicates that local orientation analysis supplies an efficient framework for FKP representation. In this paper, we propose a novel FKP recognition method using the Adaptive Steerable Orientation Coding (ASOC). High order steerable filters are first employed to extract the continuous orientation feature map, then we use multilevel histogram thresholding method to quantize the feature map adaptively and the discrete orientations are used for coding a FKP image. Furthermore, we measure the similarity between two coded FKP images by designing an effective angular matching function. Experimental results on the PolyU FKP database demonstrate the accuracy of the proposed method.
KeywordsBiometrics finger-knuckle-print steerable filter local orientation
Unable to display preview. Download preview PDF.
- 5.Yue, F., Zuo, W., Zhang, D.: ICP Registration using Principal Line and Orientation Features for Palmprint Alignment. In: Proc. ICIP, pp. 3069–3072 (2010)Google Scholar
- 6.Zhang, L.: PolyU Finger-knuckle-print Database, http://www4.comp.polyu.edu.hk/~biometrics/FKP.htm
- 9.Kong, W., Zhang, D.: Competitive Coding Scheme for Palmprint Verification. In: Proc. ICIP (2004)Google Scholar
- 10.Luessi, M., Eichmann, M., Schuster, G., Katsaggelos, A.: Framework for Efficient Optimal Multilevel Image Thresholding. Journal of Electronic Imaging 18 (2009)Google Scholar