1 option
Face biometrics for personal identification : multi-sensory multi-modal systems / Riad I. Hammoud, Besma Abidi, Mongi A. Abidi (eds.).
LIBRA TA1650 .F322 2007
Available from offsite location
- Format:
- Book
- Series:
- Signals and communication technology
- Language:
- English
- Subjects (All):
- Human face recognition (Computer science).
- Biometric identification.
- Physical Description:
- xv, 275 pages : illustrations ; 24 cm.
- Place of Publication:
- Berlin ; New York : Springer, [2007]
- Summary:
- This book provides an ample coverage of theoretical and experimental state-of-the-art work as well as new trends and directions in the biometrics field. It offers students and software engineers a thorough understanding of how some core low-level building blocks of a multi-biometric system are implemented. While this book covers a range of biometric traits including facial geometry, 3D ear form, fingerprints, vein structure, voice, and gait, its main emphasis is placed on multi-sensory and multi-modal face biometrics algorithms and systems. "Multi-sensory" refers to combining data from two or more biometric sensors, such as synchronized reflectance-based and temperature-based face images. "Multi-modal" biometrics means fusing two or more biometric modalities, like face images and voice timber. This practical reference contains four distinctive parts and a brief introduction chapter. The first part addresses new and emerging face biometrics. Emphasis is placed on biometric systems where single sensor and single modality are employed in challenging imaging conditions. The second part on multi-sensory face biometrics deals with the personal identification task in challenging variable illuminations and outdoor operating scenarios by employing visible and thermal sensors. The third part of the book focuses on multi-modal face biometrics by integrating voice, ear, and gait modalities with facial data. The last part presents generic chapters on multi-biometrics fusion methodologies and performance prediction techniques.
- Contents:
- 1.1 Motivations, General Addressed Problems, Trends, Terminologies 1
- 1.2 Inside This Book 2
- 1.3 Evaluation of This Book 5
- Part I Space/Time Emerging Face Biometrics
- 2 Pose and Illumination Invariant Face Recognition Using Video Sequences / Amit K. Roy-Chowdhury, Yilei Xu 9
- 2.1.2 Relation to Previous Work 10
- 2.2 Integrating Illumination and Motion Models in Video 13
- 2.3 Learning Joint Illumination and Motion Models from Video 16
- 2.3.1 Algorithm 17
- 2.3.2 Handling Occlusions 17
- 2.4 Face Recognition From Video 18
- 2.5 Experimental Results 20
- 2.5.1 Tracking and Synthesis Results 20
- 2.5.2 Face Recognition Results 22
- 3 Recognizing Faces Across Age Progression / Narayanan Ramanathan, Rama Chellappa 27
- 3.1.1 Previous work on Age Progression 27
- 3.1.2 Problem Statement 30
- 3.2 Age Difference Classifier 31
- 3.2.1 Bayesian Framework 32
- 3.2.2 Experiments and Results 35
- 3.3 Facial Similarity 36
- 3.4 Craniofacial Growth Model 38
- 3.4.1 Model Computation: An Optimization Problem 39
- 4 Quality Assessment and Restoration of Face Images in Long Range/High Zoom Video / Yi Yao, Besma Abidi, Mongi Abidi 43
- 4.1.3 Chapter Organization 46
- 4.2 Database Acquisition 46
- 4.2.1 Indoor Sequence Acquisition 47
- 4.2.2 Outdoor Sequence Acquisition 49
- 4.3 Face Image Quality Assessment 49
- 4.3.1 Face Recognition Rate vs. System Magnification 49
- 4.3.2 Adaptive Sharpness Measures 50
- 4.3.3 Image Sharpness and System Magnification 53
- 4.4 Face Image Enhancement 54
- 4.5 Result Validation 56
- 5 Core Faces: A Shift-Invariant Principal Component Analysis (PCA) Correlation Filter Bank for Illumination-Tolerant Face Recognition / Marios Savvides, B. V.K. Vijaya Kumar, Pradeep K. Khosla 61
- 5.1.1 Advanced Correlation Filters 62
- 5.2 Eigenphases vs. Eigenfaces 64
- 5.3 CoreFaces 68
- Part II Multi-Sensory Face Biometrics
- 6 Towards Person Authentication by Fusing Visual and Thermal Face Biometrics / Ognjen Arandjelovic, Riad Hammoud, Roberto Cipolla 75
- 6.1.1 Mono-Sensor Based Techniques 75
- 6.1.2 Multi-Sensor Based Techniques 77
- 6.2 Method Details 77
- 6.2.1 Matching Image Sets 77
- 6.2.2 Data Preprocessing and Feature Extraction 79
- 6.2.3 Single Modality-Based Recognition 80
- 6.2.4 Fusing Modalities 81
- 6.2.5 Dealing with Glasses 83
- 6.3 Empirical Evaluation 84
- 6.3.1 Results 85
- 7 Multispectral Face Recognition: Fusion of Visual Imagery with Physiological Information / Pradeep Buddharaju, Ioannis Pavlidis 91
- 7.2 Physiological Feature Extraction from Thermal Images 92
- 7.2.1 Face Segmentation 92
- 7.2.2 Segmentation of Superficial Blood Vessels 96
- 7.2.3 Extraction of TMPs 99
- 7.2.4 Matching of TMPs 100
- 7.3 PCA-Based Feature Extraction from Visual Images 102
- 7.4 Experimental Results and Discussion 103
- 8 Feature Selection for Improved Face Recognition in Multisensor Images / Satyanadh Gundimada, Vijayan Asari 109
- 8.1.1 Sensors and Systems 109
- 8.1.3 Proposed Methodologies 110
- 8.2 Phase Congruency Features 111
- 8.3 Feature Selection 113
- 8.4 Image Fusion 114
- 8.4.1 Data Level fusion 115
- 8.4.2 Decision Level Fusion 115
- 8.5 Experimental Results 115
- Part III Multimodal Face Biometrics
- 9 Multimodal Face and Speaker Identification for Mobile Devices / Timothy J. Hazen, Eugene Weinstein, Bernd Heisele, Alex Park, Ji Ming 123
- 9.2 Person Identification Technologies 124
- 9.2.1 Speaker Identification 124
- 9.2.2 Face Identification 126
- 9.2.3 Multimodal Fusion 128
- 9.3 Multimodal Person ID on a Handheld Device 128
- 9.3.2 Data Collection 128
- 9.3.3 Training 130
- 9.3.4 Face Detection Issues 130
- 9.3.5 Experimental Results 130
- 9.4 The Use of Dynamic Lip-Motion Information 132
- 9.5 Noise Robust Speaker Identification 134
- 9.5.1 The Posterior Union Model 134
- 9.5.2 Universal Compensation 135
- 9.5.3 Experimental Results 136
- 10 Quo Vadis: 3D Face and Ear Recognition? / I. Kakadiaris, G. Passalis, G. Toderici, N. Murtuza, T. Theoharis 139
- 10.2.1 Face Recognition 140
- 10.2.2 Ear Recognition 141
- 10.3.1 Generic 3D-Driven Recognition System 142
- 10.3.2 Data Preprocessing 143
- 10.3.3 Annotated Model 144
- 10.3.4 Alignment 144
- 10.3.5 Deformable Model Fitting 145
- 10.3.6 Geometry Image Representation 146
- 10.3.7 Distance Metrics 148
- 10.4 3D Face Recognition 150
- 10.4.1 Databases 150
- 10.4.2 Results 150
- 10.4.4 3D Face Recognition Hardware Prototype 156
- 10.5 3D Ear Recognition 157
- 10.5.1 Ear-Specific Issues 157
- 10.5.2 Annotated Ear Model 158
- 10.5.3 Ear-Specific Algorithm 159
- 10.5.4 3D Ear Databases 160
- 10.5.5 Results 161
- 11 Human Recognition at a Distance in Video by Integrating Face Profile and Gait / Xiaoli Zhou, Bir Bhanu, Ju Han 165
- 11.2 Technical Approach 166
- 11.2.1 High-Resolution Image Construction for Face Profile 167
- 11.2.2 Face Profile Recognition 170
- 11.2.3 Gait Recognition 175
- 11.2.4 Integrating Face Profile and Gait for Recognition at a Distance 177
- 11.3 Experimental Results 178
- 11.3.1 Data 178
- 11.3.2 Experiments 178
- Part IV Generic Approaches to Multibiometric Systems
- 12 Fusion Techniques in Multibiometric Systems / Arun Ross, Anil K. Jain 185
- 12.2 Multibiometric Systems 188
- 12.3 Taxonomy of Multibiometric Systems 190
- 12.4 Levels of Fusion 193
- 12.4.1 Sensor-Level Fusion 193
- 12.4.2 Feature-Level Fusion 196
- 12.4.3 Score-Level Fusion 200
- 12.4.4 Rank-Level Fusion 207
- 12.4.5 Decision-Level Fusion 208
- 13 Performance Prediction Methodology for Multibiometric Systems / Natalia A. Schmid, Joseph A. O'Sullivan 213
- 13.2 Stochastic Model for Multimodal Biometric Signatures 215
- 13.3 Performance of a Multimodal Biometric Recognition System with M Templates 216
- 13.3.1 Exponential Error Rate Analysis 218
- 13.4 Recognition Capacity 221
- 13.5.1 M-ary Gaussian Example 222
- 13.5.2 Capacity of the Multimodal System Based on PCA Signatures of the Face and Iris 225.
- Notes:
- Includes bibliographical references (pages [247]-271) and index.
- ISBN:
- 3540493441
- 9783540493440
- OCLC:
- 74969537
The Penn Libraries is committed to describing library materials using current, accurate, and responsible language. If you discover outdated or inaccurate language, please fill out this feedback form to report it and suggest alternative language.