Feature Selection for Finger Knuckle Print-based Multimodal Biometric System

In this paper, feature level fusion of finger knuckle prints (FKP‟s) is implemented. To overcome the curse of dimensionality, feature selection using the triangular norms is proposed. There has been no effort on feature selection using the t-norms in the literature. In this paper we address the problem of feature selection on the finger knuckle print using the t-norms. An unknown parameter in t-norms is learnt using Reinforced Hybrid evolutionary technique. Feature level fusion is performed by combining the significant features of all FKP‟s. Results show an improvement in the accuracy when the features are selected by a divergence function derived from the new entropy function using t-norms on two pairs of training features taken at a time. Results of both identification and verification rates show a significant improvement in the performance with feature level fusion.

[1]  Pasi Luukka,et al.  Feature selection using fuzzy entropy measures with similarity classifier , 2011, Expert Syst. Appl..

[2]  Lei Liu,et al.  Feature selection with dynamic mutual information , 2009, Pattern Recognit..

[3]  David Zhang,et al.  Online finger-knuckle-print verification for personal authentication , 2010, Pattern Recognit..

[4]  Madasu Hanmandlu,et al.  Content-based Image Retrieval by Information Theoretic Measure , 2011 .

[5]  Kazuyuki Murase,et al.  A new wrapper feature selection approach using neural network , 2010, Neurocomputing.

[6]  Andrew Beng Jin Teoh,et al.  Touch-Less Palm Print Biometric System , 2008, VISAPP.

[7]  Iti Saha Misra,et al.  IMPROVED ADAPTIVE BACTERIA FORAGING ALGORITHM IN OPTIMIZATION OF ANTENNA ARRAY FOR FASTER CONVERGENCE , 2008 .

[8]  Josep M. Sopena,et al.  Performing Feature Selection With Multilayer Perceptrons , 2008, IEEE Transactions on Neural Networks.

[9]  Ajay Kumar,et al.  Personal identification using finger knuckle orientation features , 2009 .

[10]  Witold Pedrycz,et al.  Fuzzy Sets and T-Norms in the Light of Fuzzy Logic , 1988, Int. J. Man Mach. Stud..

[11]  Wael Mansour Korani.  Bacterial foraging oriented by Particle Swarm Optimization strategy for PID tuning , 2009, 2009 IEEE International Symposium on Computational Intelligence in Robotics and Automation - (CIRA).

[12]  Miguel A. Ferrer,et al.  Improved finger-knuckle-print authentication based on orientation enhancement , 2011 .

[13]  Uzay Kaymak,et al.  Fuzzy criteria for feature selection , 2012, Fuzzy Sets Syst..

[14]  Amparo Alonso-Betanzos,et al.  Combining functional networks and sensitivity analysis as wrapper method for feature selection , 2011, Expert Syst. Appl..

[15]  Richard Weber,et al.  A wrapper method for feature selection using Support Vector Machines , 2009, Inf. Sci..

[16]  David Zhang,et al.  Ensemble of local and global information for finger-knuckle-print recognition , 2011, Pattern Recognit..

[17]  Jin Young Choi,et al.  Theoretical analysis on feature extraction capability of class-augmented PCA , 2009, Pattern Recognit..

[18]  Cheng-Lung Huang,et al.  A distributed PSO-SVM hybrid system with feature selection and parameter optimization , 2008, Appl. Soft Comput..

[19]  Duoqian Miao,et al.  A rough set approach to feature selection based on ant colony optimization , 2010, Pattern Recognit. Lett..

[20]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Jose Miguel Puerta,et al.  A GRASP algorithm for fast hybrid (filter-wrapper) feature subset selection in high-dimensional datasets , 2011, Pattern Recognit. Lett..