Bouridane Imaging for Forensics and Security

From Theory to Practice
1. Auflage 2009
ISBN: 978-0-387-09532-5
Verlag: Springer
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 212 Seiten

Reihe: Signals and Communication Technology

Imaging for Forensics and Security: From Theory to Practice provides a detailed analysis of new imaging and pattern recognition techniques for the understanding and deployment of biometrics and forensic techniques as practical solutions to increase security. It contains a collection of the recent advances in the technology ranging from theory, design, and implementation to performance evaluation of biometric and forensic systems. This book also contains new methods such as the multiscale approach, directional filter bank, and wavelet maxima for the development of practical solutions to biometric problems. The book introduces a new forensic system based on shoeprint imagery with advanced techniques for use in forensics applications. It also presents the concept of protecting the originality of biometric images stored in databases against intentional and unintentional attacks and fraud detection data in order to further increase the security.

Autoren/Hrsg.

Bouridane, Ahmed

Inhaltsverzeichnis

1;Preface;7
2;Contents;12
3;1 Introduction and Preliminaries on Biometricsand Forensics Systems;17
3.1;1.1 Introduction;17
3.2;1.2 Definition of Biometrics;17
3.2.1;1.2.1 Biometric Characteristics;18
3.2.2;1.2.2 Biometric Modalities;18
3.3;1.3 Recognition/Verification/Watch-List;21
3.3.1;1.3.1 Verification: Am I Who I Claim to Be?;21
3.3.2;1.3.2 Recognition: Who Am I?;21
3.3.3;1.3.3 The Watch-List: Are You Looking for Me?;22
3.4;1.4 Steps of a Typical Biometric Recognition Application;22
3.4.1;1.4.1 Biometric Data Localisation;22
3.4.2;1.4.2 Normalisation and Pre-processing;23
3.4.3;1.4.3 Feature Extraction;24
3.4.4;1.4.4 Matching;25
3.4.5;1.4.5 Databases;25
3.5;1.5 Summary;25
3.6;References;26
4;2 Data Representation and Analysis;27
4.1;2.1 Introduction;27
4.2;2.2 Data Acquisition;28
4.2.1;2.2.1 Sensor Module;29
4.2.2;2.2.2 Data Storage;30
4.2.2.1;2.2.2.1 Raw Images;30
4.2.2.2;2.2.2.2 Feature Sets;30
4.3;2.3 Feature Extraction;31
4.4;2.4 Matcher;32
4.5;2.5 System Testing;32
4.6;2.6 Performance Evaluation;33
4.7;2.7 Conclusion;34
4.8;References;35
5;3 Improving Face Recognition Using Directional Faces;36
5.1;3.1 Introduction;36
5.2;3.2 Face Recognition Basics;37
5.2.1;3.2.1 Recognition/Verification;37
5.2.1.1;3.2.1.1 Face Verification: Am I Who I Claim to be?;37
5.2.1.2;3.2.1.2 Face Recognition: Who am I?;37
5.2.1.3;3.2.1.3 The Watch-List: Are You Looking for Me?;38
5.2.2;3.2.2 Steps of a Typical Face Recognition Application;38
5.2.2.1;3.2.2.1 Face Localisation;38
5.2.2.2;3.2.2.2 Normalisation and Pre-processing;39
5.2.2.3;3.2.2.3 Feature Extraction;40
5.2.2.4;3.2.2.4 Matching;41
5.3;3.3 Previous Work;41
5.3.1;3.3.1 Principal Component Analysis (PCA);41
5.3.2;3.3.2 Independent Component Analysis (ICA);42
5.3.3;3.3.3 Linear Discriminant Analysis (LDA);43
5.3.4;3.3.4 Subspace Discriminant Analysis (SDA);44
5.3.4.1;3.3.4.1 Dividing Classes into Subclasses;44
5.3.4.2;3.3.4.2 NN-Clustering;45
5.4;3.4 Face Recognition Using Filter Banks;46
5.4.1;3.4.1 Gabor Filter Bank;46
5.4.1.1;3.4.1.1 Gabor Functions and Wavelets;46
5.4.1.2;3.4.1.2 Gabor Filter Dictionary Design;47
5.4.1.3;3.4.1.3 Augmented Gabor-Face Vector;47
5.4.2;3.4.2 Directional Filter Bank: A Review;48
5.4.2.1;3.4.2.1 Analysis Filters;49
5.4.2.2;3.4.2.2 Quincunx Downsampling;50
5.4.2.3;3.4.2.3 Overview of --band DFB;50
5.4.2.4;3.4.2.4 Directional Images;51
5.5;3.5 Proposed Method and Results Analysis;52
5.5.1;3.5.1 Proposed Method;52
5.5.2;3.5.2 PCA;53
5.5.3;3.5.3 ICA;54
5.5.4;3.5.4 LDA;56
5.5.5;3.5.5 SDA;56
5.5.6;3.5.6 FERET Database Results;58
5.6;3.6 Conclusion;59
5.7;References;60
6;4 Recent Advances in Iris Recognition: A Multiscale Approach;64
6.1;4.1 Introduction;64
6.2;4.2 Related Work: A Review;66
6.3;4.3 Iris Localisation;67
6.3.1;4.3.1 Background;67
6.3.2;4.3.2 Iris Segmentation;67
6.3.3;4.3.3 Existing Methods for Iris Localisation;68
6.3.3.1;4.3.3.1 Daugmans Integro-Differential Operator;68
6.3.3.2;4.3.3.2 Hough Transform;69
6.3.3.3;4.3.3.3 Discrete Circular Active Contours;69
6.4;4.4 Proposed Method for Iris Localisation;70
6.4.1;4.4.1 Motivation;70
6.4.1.1;4.4.1.1 Edge Detector Using Wavelets;70
6.4.1.2;4.4.1.2 Multiscale Edge Detection;71
6.4.2;4.4.2 The Multiscale Method;72
6.4.2.1;4.4.2.1 Edge Map Detection;72
6.4.2.2;4.4.2.2 Iris Outer and Pupil Circle Detection;77
6.4.2.3;4.4.2.3 Eyelids and Eyelashes Isolating;78
6.4.2.4;4.4.2.4 Iris Normalisation and Polar Transformation;78
6.4.3;4.4.3 Results and Analysis;80
6.5;4.5 Texture Analysis and Feature Extraction;81
6.5.1;4.5.1 Wavelet Maxima Components;83
6.5.2;4.5.2 Special Gabor Filter Bank;83
6.5.3;4.5.3 Proposed Method;85
6.5.3.1;4.5.3.1 Template Generation;86
6.6;4.6 Matching;86
6.7;4.7 Experimental Results and Analysis;87
6.7.1;4.7.1 Database;87
6.7.2;4.7.2 Combined Multiresolution Feature Extraction Techniques;87
6.7.3;4.7.3 Template Computation;88
6.7.4;4.7.4 Comparison with Existing Methods;88
6.8;4.8 Discussion and Future Work;89
6.9;4.9 Conclusion;90
6.10;References;90
7;5 Spread Transform Watermarking Using Complex Wavelets;93
7.1;5.1 Introduction;93
7.2;5.2 Wavelet Transforms;93
7.2.1;5.2.1 Dual Tree Complex Wavelet Transform;94
7.2.2;5.2.2 Non-redundant Complex Wavelet Transform;97
7.3;5.3 Visual Models;100
7.3.1;5.3.1 Chou's Model;101
7.3.2;5.3.2 Loo's Model;107
7.3.3;5.3.3 Hybrid Model;108
7.4;5.4 Watermarking as Communication with Side Information;108
7.4.1;5.4.1 Quantisation Index Modulation;110
7.4.2;5.4.2 Spread Transform Watermarking;111
7.5;5.5 Proposed Algorithm;112
7.5.1;5.5.1 Encoding of Watermark;113
7.5.2;5.5.2 Decoding of Watermark;114
7.6;5.6 Information Theoretic Analysis;114
7.6.1;5.6.1 Decoding of Watermark;115
7.6.2;5.6.2 Parallel Gaussian Channels;116
7.6.3;5.6.3 Watermarking Game;119
7.6.4;5.6.4 Non-iid Data;124
7.6.5;5.6.5 Fixed Embedding Strategies;125
7.7;5.7 Conclusion;126
7.8;References;127
8;6 Protection of Fingerprint Data Using Watermarking;130
8.1;6.1 Introduction;130
8.2;6.2 Generic Watermarking System;132
8.3;6.3 State-of-the-Art;136
8.4;6.4 Optimum Watermark Detection;137
8.5;6.5 Statistical Data Modelling and Application to Watermark Detection;140
8.5.1;6.5.1 Laplacian and Generalised Gaussian Models;141
8.5.2;6.5.2 Alpha Stable Model;142
8.6;6.6 Experimental Results;143
8.6.1;6.6.1 Experimental Modelling of DWT Coefficients;145
8.6.2;6.6.2 Experimental Watermarking Results;148
8.6.2.1;6.6.2.1 Imperceptibility Analysis;148
8.6.2.2;6.6.2.2 Detection Performance;149
8.7;6.7 Conclusions;151
8.8;References;152
9;7 Shoemark Recognition for Forensic Science: An EmergingTechnology;155
9.1;7.1 Background to the Problem of Shoemark Forensic Evidence;155
9.1.1;7.1.1 Applications of a Shoemark in Forensic Science;156
9.1.2;7.1.2 The Need for Automating Shoemark Classification;158
9.1.3;7.1.3 Inconsistent Classification;159
9.1.4;7.1.4 Importable Classification Schema;160
9.1.5;7.1.5 Shoemark Processing Time Restrictions;161
9.2;7.2 Collection of Shoemarks at Crime Scenes;161
9.2.1;7.2.1 Shoemark Collection Procedures;162
9.2.2;7.2.2 Transfer/Contact Shoemarks;162
9.2.3;7.2.3 Photography of Shoemarks;163
9.2.4;7.2.4 Making Casts of Shoemarks;164
9.2.5;7.2.5 Gelatine Lifting of Shoemarks;165
9.2.6;7.2.6 Electrostatic Lifting of Shoemarks;165
9.2.7;7.2.7 Recovery of Shoemarks from Snow;166
9.2.8;7.2.8 Recovery of Shoemarks using Perfect Shoemark Scan;166
9.2.9;7.2.9 Making a Cast of a Shoemark Directly from a Suspect's Shoe;167
9.2.10;7.2.10 Processing of Shoemarks;167
9.2.11;7.2.11 Entering Data into a Computerised System;169
9.3;7.3 Typical Methods for Shoemark Recognition;169
9.3.1;7.3.1 Feature-Based Classification;170
9.3.2;7.3.2 Classification Based on Accidental Characteristics;171
9.4;7.4 Review of Shoemark Classfication Systems;172
9.4.1;7.4.1 SHOE-FIT;172
9.4.2;7.4.2 SHOE©;172
9.4.3;7.4.3 Alexandre's System;173
9.4.4;7.4.4 REBEZO;173
9.4.5;7.4.5 TREADMARK TM ;174
9.4.6;7.4.6 SICAR;174
9.4.7;7.4.7 SmART;174
9.4.8;7.4.8 De Chazal's System;175
9.4.9;7.4.9 Zhang's System;175
9.5;References;175
10;8 Techniques for Automatic Shoeprint Classification;177
10.1;8.1 Current Approaches;177
10.2;8.2 Using Phase-Only Correlation;177
10.2.1;8.2.1 The POC Function;178
10.2.2;8.2.2 Translation and Brightness Properties of the POC Function;180
10.2.3;8.2.3 The Proposed Phase-Based Method;180
10.2.3.1;8.2.3.1 Spectral Weighting Function;180
10.2.3.2;8.2.3.2 Shoeprints Matching Algorithm;181
10.2.4;8.2.4 Experimental Results;182
10.3;8.3 Deployment of ACFs;184
10.3.1;8.3.1 Shoeprint Classification Using ACFs;185
10.3.2;8.3.2 Matching Metrics;187
10.3.3;8.3.3 Optimum Trade-Off Synthetic Discriminant Function Filter;188
10.3.4;8.3.4 Unconstrained OTSDF Filter;189
10.3.5;8.3.5 Tests and Results;190
10.4;8.4 Conclusion;191
10.5;References;192
11;9 Automatic Shoeprint Image Retrieval Using Local Features ;193
11.1;9.1 Motivations;193
11.2;9.2 Local Image Features;193
11.2.1;9.2.1 New Local Feature Detector: Modified Harris--Laplace Detector;194
11.2.1.1;9.2.1.1 Modified Harris--Laplace (MHL) Detector;195
11.2.1.2;9.2.1.2 Repeatability Evaluation;197
11.2.2;9.2.2 Local Feature Descriptors;198
11.2.3;9.2.3 Similarity Measure;200
11.3;9.3 Experimental Results;201
11.3.1;9.3.1 Shoeprint Image Databases;201
11.4;9.4 Summary;210
11.5;References;212
12;Index;214