Swarm Intelligence for Iris Recognition

Iris recognition is one of the highest accuracy techniques used in biometric systems. The accuracy of the iris recognition system is measured by False Reject Rate (FRR), which measures the authenticity of a user who is incorrectly rejected by the system due to changes in iris features (such as aging and health condition) and external factors that affect iris image, for instance, high noise rate. External factors such as technical fault, occlusion, and source of lighting that causes the image acquisition to produce distorted iris images create error, hence are incorrectly rejected by the biometric system. FRR can be reduced using wavelets and Gabor filters, cascaded classifiers, ordinal measures, multiple biometric modalities, and a selection of unique iris features. Nonetheless, in the long duration of the matching process, existing methods were unable to identify the authenticity of the user since the iris structure itself produces a template changed due to aging. In fact, the iris consists of unique features such as crypts, furrows, collarette, pigment blotches, freckles, and pupils that are distinguishable among humans. Earlier research was done by selecting unique iris features. However, these had low accuracy levels. A new way of identifying and matching the iris template using the nature-inspired algorithm is described in this book. It provides an overview of iris recognition that is based on nature-inspired environment technology. The book is useful for students from universities, polytechnics, community colleges; practitioners; and industry practitioners. Cover Title Page Copyright Page Preface Acknowledgement Table of Contents List of Figures 1. Introduction 2. Human Eye 2.1 Overview 2.2 Iris Structure 2.3 The Use of Iris for Biometric System 2.4 Summary 3. The First Phase of Iris Recognition 3.1 Overview 3.2 Enrolment Process 3.2.1 Image Acquisition and Iris Database 3.2.2 Circular Segmentation and Normalization 3.2.3 Extraction 3.3 Iris Template Storage 3.4 Comparison Process 3.4.1 Identification (Comparison for One-to-Many) 3.4.2 Verification (Comparison for One-to-One) 3.5 Challenges in the First Phase of Iris Recognition 3.5.1 Cost of Biometrics System 3.5.2 Threats and Attacks in Biometrics 3.5.3 Hardware and Software Limitations 3.5.4 Iris Distortion 3.5.5 Handling Poor Quality Data 3.6 Summary 4. The Second Phase of Iris Recognition 4.1 Overview 4.2 Short Range Iris Recognition 4.2.1 Non-Circular Segmentation 4.2.2 Artificial Intelligence Based Segmentation and Normalization 4.3 Long Range Iris Recognition 4.3.1 Iris Detection at-a-Distance (IAAD) Framework 4.4 Challenges in Second Phase of Iris Recognition 4.4.1 Pre-processing 4.4.2 Feature Extraction 4.4.3 Template Matching 4.4.4 Sensors 4.4.5 Iris Template Security 4.5 Summary 5. Swarm-Inspired Iris Recognition 5.1 Overview 5.2 Ant Colony Optimization 5.2.1 ACO Algorithm 5.2.2 ACO Pseudocode 5.2.3 Case Study: Enhanced ACO based Extraction of Iris Template 5.2.4 The Experiment Results and Findings 5.3 Particle Swarm Optimization 5.3.1 PSO Algorithm 5.3.2 Case Study: The Proposed Design and Approach Method 5.3.3 Identification Phase in Iris Recognition System 5.3.4 Hamming Distance of Intra-Class Image 5.3.5 FAR and FRR Value 5.4 Discussions 5.5 Summary 6. Conclusion References Index "Iris recognition has been widely recognized as one of the most performing biometric system. The accuracy performance of iris recognition system is measured by FRR (False Reject Rate). FRR measures the genuine user who is incorrectly denied by the system due to the changes in iris features (such as aging and health condition) and external factors that affected the iris image to be high in noise rate. The external factors such as technical fault, occlusion, and source of lighting caused the image acquisition to produce distorted iris images problem hence incorrectly rejected by the biometric system. The current way of reducing FRR are wavelets and Gabor filters, cascaded classifiers, ordinal measure, multiple biometric modality and selection of unique iris features. Nonetheless, in the long duration of matching process, the previous methods unable to identify the user as a genuine since the iris structure itself produce a template changed due to aging. In facts, iris consists of unique features such as crypts, furrows, collarette, pigment blotches, freckles and pupil that are distinguishable among human. Previous research has been done in selecting the unique iris features however it shows low accuracy performance. Therefore, a new way of identifying and matching the iris template using nature-inspired algorithm is proposed in this book. As a conclusion, this book entitled as "Swarm Intelligence for Iris Recognition" brings an overview of iris recognition that naturally based on nature-inspired environment technology and provides benefits to the reader"-- Provided by publisher Swarm intelligence has been one of the methods of natural computing that falls under the artificial intelligence. The swarm intelligence is the winning algorithm since it searches for the genuine user effectively and tolerates with high noise in the iris template during the matching process in the iris recognition.