Establishing PNN-Based Iris Code to Identity Fuzzy Membership for Consistent Enrollment

This paper presents the recognition performances of a simulated multi-enrollment iris biometric verification system in which the fuzzy membership of any current user to an enrolled identity that he is claiming is decided using a probabilistic neural network architecture that has two roles: first, it encodes from five binary iris code samples the digital identity of each enrolled person (eye), and second, it uses the enrolled digital identities to produce similarity scores as membership degrees of the current candidate iris codes to the claimed identities. The experimental part contains two simulations of a recognition system having 654 users, each of them enrolled with five eye images (and the corresponding binary iris codes). The first simulation uses five candidate iris codes for each enrolled user (which gives a total of 3.270 candidate iris codes), whereas the second one is testing the identity claims for all the candidate iris codes corresponding to the eyes having at least five candidate iris codes available (giving a total of 8.810 candidate iris codes). Both simulations use CASIA-Iris-Lamp (V4) database.

[1]  Zhuoda Jiang,et al.  Support vector machines for multi-class pattern recognition based on improved voting strategy , 2010, 2010 Chinese Control and Decision Conference.

[2]  Jamal Ahmad Dargham,et al.  Iris recognition using self-organizing neural network , 2002, Student Conference on Research and Development.

[3]  Valentina Emilia Balas,et al.  Learning Iris Biometric Digital Identities for Secure Authentication: A Neural-Evolutionary Perspective Pioneering Intelligent Iris Identification , 2012, Recent Advances in Intelligent Engineering Systems.

[4]  P. Bhattacharya,et al.  Multi-class SVM based iris recognition , 2007, 2007 10th international conference on computer and information technology.

[5]  John Daugman.  How iris recognition works , 2004 .

[6]  A. M. Turing,et al.  Computing Machinery and Intelligence , 1950, The Philosophy of Artificial Intelligence.

[7]  Valentina Emilia Balas,et al.  Iris codes classification using discriminant and witness directions , 2011, 2011 5th International Symposium on Computational Intelligence and Intelligent Informatics (ISCIII).

[8]  Nooritawati Md Tahir,et al.  Half iris Gabor based iris recognition , 2014, 2014 IEEE 10th International Colloquium on Signal Processing and its Applications.

[9]  Jason Weston,et al.  Support vector machines for multi-class pattern recognition , 1999, ESANN.

[10]  Valentina Emilia Balas,et al.  8-valent fuzzy logic for iris recognition and biometry , 2011, 2011 5th International Symposium on Computational Intelligence and Intelligent Informatics (ISCIII).

[11]  Rodrigo Salas,et al.  Zernike's Feature Descriptors for Iris Recognition with SVM , 2011, 2011 30th International Conference of the Chilean Computer Science Society.

[12]  G. N. Shinde,et al.  Iris Recognition Using Fuzzy Min-Max Neural Network , 2011 .

[13]  Prabir Bhattacharya,et al.  Iris Recognition with Support Vector Machines , 2006, ICB.

[14]  A. J. Ayer,et al.  Language, Truth, and Logic , 1936 .

[15]  Ching-Han Chen,et al.  High performance iris recognition based on LDA and LPCC , 2005, 17th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'05).

[16]  Valentina Emilia Balas,et al.  The Biometric Menagerie - A Fuzzy and Inconsistent Concept , 2012, SOFA.

[17]  Chia-Te Chu,et al.  Low complexity iris recognition based on wavelet probabilistic neural networks , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[18]  Libor Masek,et al.  Recognition of Human Iris Patterns for Biometric Identification , 2003 .

[19]  Valentina Emilia Balas,et al.  Exploratory simulation of an Intelligent Iris Verifier Distributed System , 2011, 2011 6th IEEE International Symposium on Applied Computational Intelligence and Informatics (SACI).

[20]  Valentina E. Balas,et al.  Fuzzy Membership, Possibility, Probability and Negation in Biometrics , 2014 .

[21]  Valentina Emilia Balas,et al.  Comparing Haar-Hilbert and Log-Gabor based iris encoders on Bath Iris Image Database , 2010, 4th International Workshop on Soft Computing Applications.

[22]  Kang Ryoung Park,et al.  Super-Resolution Method Based on Multiple Multi-Layer Perceptrons for Iris Recognition , 2009, Proceedings of the 4th International Conference on Ubiquitous Information Technologies & Applications.

[23]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[24]  Nicolaie Popescu-Bodorin,et al.  Exploring New Directions in Iris Recognition , 2009, SYNASC.

[25]  Mei Xie,et al.  Iris matching using ferns classifier , 2012, 2012 International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP).

[26]  Patrick K. Simpson,et al.  Fuzzy min-max neural networks. I. Classification , 1992, IEEE Trans. Neural Networks.

[27]  V. Vapnik.  Estimation of Dependences Based on Empirical Data , 2006 .

[28]  Richa Singh,et al.  Belief Function Theory Based Biometric Match Score Fusion: Case Studies in Multi-instance and Multi-unit Iris Verification , 2009, 2009 Seventh International Conference on Advances in Pattern Recognition.

[29]  K.W. Bowyer,et al.  The Best Bits in an Iris Code , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Yong Wang,et al.  Iris Recognition Using Support Vector Machines , 2004, ISNN.

[31]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.