声明
CONTENTS
ABSTRACT
INTRODUCTION
1．1 RESEARCH BACKGROUND
1．2 FINGER VEIN RECOGNITION
1．2．1 The Significance of Finger Vein Recognition
1．2．2 Research Status of Finger Vein Recognition
1．2．3 Material
1．3 Contribution
1．4 Thesis Structure
Chapter 2 Related Work
2．1 Steps of Finger Vein Recognition
2．2 Image Acquisition
2．3 Preprocessing
2．3．1 Image Quality Assessment
2．3．2 ROI Extraction
2．3．3 Normalization and Enhancement
2．4 Feature Extraction
2．4．1 Vein Based Method
2．4．2 Local Binary-Based(LBP)Method
2．4．3 Dimensionality Reduction-Based Method
2．4．3 Minutiae Point-Based Method
2．5 Matching
2．6 Performance Analysis
2．6．1 Conventional Finger Vein Recognition Method
2．6．2 Traditional Machine Learning Finger vein Recognition Methods
2．6．3 Finger Vein Recognition Using Deep Learning Methods
2．7 Problem Statement
2．7．1 Image Quality Assessment
2．7．2 Image Enhancement
Chapter 3 Proposed Novel Image Quality Assessment and Enhancement Techniques for Finger Vein Recognition
3．1 Introduction
3．2 Our Method
3．3 Feature Selection
3．3．1 Gradient
3．3．2 Entropy
3．3．3 Information Capacity
3．4 Image Quality Evaluation Using Decision Tree With R-SMOTE Technique
3．5 Finger Vein Image Enhancement Methods
3．5．1 Single Scale Retinex With Chromaticity Preserved Algorithm
3．5．2 Gaussian Filter
Chapter 4 Experimental Result
4．1 Database and Tools
4．2 Experiment Setting
4．2．1 Experiment 1
4．2．2 Experiment 2
4．2．3 Experiment 3
4．3 Conclusion
Chapter 5 Conclusion and Discussion
REFERENCES
ACKNOWLEDGEMENTS
List of Published Papers
