Iris recognition system using principal component analysis - Dissertation Example

This gives a fine demarcation between the inter class and intra class irises and hence the recognition becomes easier. Principal component analysis has been used to reduce the dimensionality. This enables choice of appropriate features from the iris templates and improves classification. The iris recognition accuracy has been described in terms of False Reject Ratio and False Accept Ratio. Table of contents Chapter 1 – Introduction of Project 1.1. Introduction 1.2. Project background 1.3. Problem Statement 1.4. Project aim and objectives 1.5. Significance of the project 1.6. Scope of project 1.7. Overview of project 2.

Chapter - 2 Review of Literature 2.1. Introduction 2.2. Human Iris System 2.2.1. Iris and Biometrics 2.2.2. Artificial Intelligence for Iris recognition 2.3. Scanning the Iris 2.3.1 Localization of Landmarks 2.3.2 Digital Imaging 2.4. statistical dependence 2.5. Principal Component Analysis 2.5.1 Covariance 2.5.2 Normality and Residuals 2.6. Chapter summary Chapter 3 – Methodology and framework of the Project 3.1. Introduction 3.2. Method 3.3. Requirements 3.4. Project Design 3.5. Hardware Design 3.6. Software Design 3.7. Chapter summary Chapter 4 – Project implementation and testing 4.1. Introduction 4.2. Image Segmentation 4.3. Image Normalisation 4.4. Feature extraction and encoding 4.5. Dimensionality Reduction 4.6. Iris matching Chapter 5 – Analysis and Discussion of Results 5.1. Introduction 5.2. Effect of the Parameters 5.3. Analysis of Hamming Distance 5.4. Recognition performance Chapter 6 – Project Management 6.1. Introduction 6.2. Project scheduling 6.3. Time management 6.4. Risk management 6.5. Quality management 6.6. Cost Management Chapter 7 - Critical Appraisal 7.1. Achievements 7.2. Future Research Chapter 8 – Conclusion Chapter 9 – Student Reflection References Appendices List of Figures Fig. 2.1.

The Iris marking process. Fig. 2.2. Iris Localization/ Hough Transform Figure 2.3. Iris Recognition Method Fig. 2.4. Iris Recognition in Java Fig.3.1. Sample eye images from CASIA database Fig. 3.2. Waterfall diagram Fig. 3.3. The UML Class diagram for the project in Smart Draw tool. Fig. 3.4. UML activity diagram for this project in Smart Draw. Fig. 4.1. Segmented eye image. Fig.4.2. Eye image with isolated iris region. Fig.5.1. Variation of intra class Standard deviation with number of shifts. Fig.5.2. Histogram of Hamming distance (intra class) without shifting of bits. Fig.5.3. Histogram of Hamming distance (intra class) with 8 times shifting of bits. Fig. 5.

4 Histogram of the hamming distances (inter class) with 8 times shifting of bits. Fig.6.1. The Gantt chart for project schedule. List of Tables Table 2.2. Characteristics Index of Biometric Variations Table 2.1 False Rejection Rate Table 6.1. Risk Management Chapter 1 – Introduction of Project 2.3. Introduction This chapter presents a brief introduction about the project in terms of the project background, the scope of the project, the aim and objectives of the project and the overview. Researchers have developed several methods to develop Biometric tools.

“A biometric system provides automatic identification of an individual based on a unique feature or characteristic possessed by the individual” (Majumder, Ray, & Singh, 2009). Among the various biometrics the Iris Recognition System uses