Muutke küpsiste eelistusi

E-raamat: Face Detection and Recognition: Theory and Practice [Taylor & Francis e-raamat]

(University of Calcutta, Kolkata, India), ,
  • Formaat: 352 pages
  • Ilmumisaeg: 23-Oct-2019
  • Kirjastus: Chapman & Hall/CRC
  • ISBN-13: 9780429157196
Teised raamatud teemal:
  • Taylor & Francis e-raamat
  • Hind: 184,65 €*
  • * hind, mis tagab piiramatu üheaegsete kasutajate arvuga ligipääsu piiramatuks ajaks
  • Tavahind: 263,78 €
  • Säästad 30%
Face Detection and Recognition: Theory and PracticeSuurem pilt
  • Formaat: 352 pages
  • Ilmumisaeg: 23-Oct-2019
  • Kirjastus: Chapman & Hall/CRC
  • ISBN-13: 9780429157196
Teised raamatud teemal:
Taylor & Francis e-raamatudRohkem infot Taylor & Francis e-raamatute kohta
Raamatu kodulehekülg: https://www.taylorfrancis.com/books/9780429157196
Face detection and recognition are the nonintrusive biometrics of choice in many security applications. Examples of their use include border control, drivers license issuance, law enforcement investigations, and physical access control.





Face Detection and Recognition: Theory and Practice

elaborates on andexplains the theory and practice of face detection and recognition systems currently in vogue. The book begins with an introduction to the state of the art, offering a general review of the available methods and an indication of future research using cognitive neurophysiology. The text then:







Explores subspace methods for dimensionality reduction in face image processing, statistical methods applied to face detection, and intelligent face detection methods dominated by the use of artificial neural networks





Covers face detection with colour and infrared face images, face detection in real time, face detection and recognition using set estimation theory, face recognition using evolutionary algorithms, and face recognition in frequency domain





Discusses methods for the localization of face landmarks helpful in face recognition, methods of generating synthetic face images using set estimation theory, and databases of face images available for testing and training systems





Features pictorial descriptions of every algorithm as well as downloadable source code (in MATLAB®/PYTHON) and hardware implementation strategies with code examples





Demonstrates how frequency domain correlation techniques can be used supplying exhaustive test results





Face Detection and Recognition: Theory and Practice provides students, researchers, and practitioners with a single source for cutting-edge information on the major approaches, algorithms, and technologies used in automated face detection and recognition.
List of Figures
xv
List of Tables
xxi
Preface xxiii
Acknowledgment xxv
1 Introduction
1(18)
1.1 Introduction
1(1)
1.2 Biometric identity authentication techniques
2(2)
1.3 Face as biometric identity
4(9)
1.3.1 Automated face recognition system
5(2)
1.3.2 Process flow in face recognition system
7(4)
1.3.3 Problems of face detection and recognition
11(1)
1.3.4 Liveness detection for face recognition
12(1)
1.4 Tests and metrics
13(3)
1.5 Cognitive psychology in face recognition
16(3)
2 Face detection and recognition techniques
19(22)
2.1 Introduction to face detection
19(2)
2.2 Feature-based approaches for face detection
21(7)
2.2.1 Low-level analysis
22(1)
2.2.1.1 Edges
22(1)
2.2.1.2 Gray-level analysis
23(1)
2.2.1.3 Color information in face detection
23(1)
2.2.1.4 Motion-based analysis
24(1)
2.2.2 Active shape model
25(1)
2.2.3 Feature analysis
26(1)
2.2.4 Image-based approaches for face detection
27(1)
2.2.5 Statistical approaches
28(1)
2.3 Face recognition methods
28(6)
2.3.1 Geometric feature-based method
29(1)
2.3.2 Subspace-based face recognition
29(2)
2.3.3 Neural network-based face recognition
31(1)
2.3.4 Correlation-based method
32(1)
2.3.5 Matching pursuit-based methods
33(1)
2.3.6 Support vector machine approach
33(1)
2.3.7 Selected works on face classifiers
34(1)
2.4 Face reconstruction techniques
34(7)
2.4.1 Three-dimensional face recognition
35(3)
2.4.1.1 Feature extraction
38(1)
2.4.1.2 Global feature extraction
38(1)
2.4.1.3 Three-dimensional morphable model
39(2)
3 Subspace-based face recognition
41(22)
3.1 Introduction
41(1)
3.2 Principal component analysis
42(7)
3.2.1 Two-dimensional principal component analysis
46(1)
3.2.2 Kernel principal component analysis
47(2)
3.3 Fisher linear discriminant analysis
49(9)
3.3.1 Fisher linear discriminant analysis for two-class case
53(5)
3.4 Independent component analysis
58(5)
4 Face detection by Bayesian approach
63(20)
4.1 Introduction
63(1)
4.2 Bayes decision rule for classification
63(12)
4.2.1 Gaussian distribution
64(5)
4.2.2 Bayes theorem
69(1)
4.2.3 Bayesian decision boundaries and discriminant function
70(2)
4.2.4 Density estimation using eigenspace decomposition
72(3)
4.3 Bayesian discriminant feature method
75(5)
4.3.1 Modelling of face and non-face pattern
76(2)
4.3.2 Bayes classification using BDF
78(2)
4.4 Experiments and results
80(3)
5 Face detection in color and infrared images
83(24)
5.1 Introduction
83(1)
5.2 Face detection in color images
84(1)
5.3 Color spaces
84(5)
5.3.1 RGB model
85(2)
5.3.2 HSI color model
87(1)
5.3.3 YCbCr color space
87(2)
5.4 Face detection from skin regions
89(1)
5.4.1 Skin modelling
89(1)
5.4.1.1 Skin color modelling explicitly from RGB space
89(1)
5.4.1.2 Skin color modelling explicitly from YCbCr space
89(1)
5.5 Probabilistic skin detection
90(2)
5.6 Face detection by localizing facial features
92(5)
5.6.1 EyeMap
93(1)
5.6.2 MouthMap
94(3)
5.7 Face detection in infrared images
97(1)
5.8 Multivariate histogram-based image segmentation
98(9)
5.8.1 Method for finding major clusters from a multivariate histogram
100(1)
5.8.2 Experiments and results on the color and IR face image datasets
101(2)
5.8.3 Utility of facial features
103(4)
6 Intelligent face detection
107(16)
6.1 Introduction
107(1)
6.2 Multilayer perceptron model
108(5)
6.2.1 Learning algorithm
110(3)
6.3 Face detection networks
113(1)
6.4 Training images
113(5)
6.4.1 Data preparation
113(2)
6.4.2 Face training
115(1)
6.4.2.1 Active learning
116(1)
6.4.3 Exhaustive training
117(1)
6.5 Evaluation of face detection for upright faces
118(5)
6.5.1 Algorithm
118(1)
6.5.2 Image scanning and face detection
119(4)
7 Real-time face detection
123(12)
7.1 Introduction
123(1)
7.2 Features
124(1)
7.3 Integral image
125(2)
7.3.1 Rectangular feature calculation from integral image
125(2)
7.4 Adaboost
127(6)
7.4.1 Modified AdaBoost algorithm
129(2)
7.4.2 Cascade classifier
131(2)
7.5 Face detection using OpenCV
133(2)
8 Face space boundary selection for face detection and recognition
135(26)
8.1 Introduction
135(2)
8.2 Face points, face classes and face space boundaries
137(1)
8.3 Mathematical preliminaries for set estimation method
138(2)
8.4 Face space boundary selection using set estimation
140(2)
8.4.1 Algorithm for global threshold-based face detection
140(2)
8.5 Experimental design and result analysis
142(4)
8.5.1 Face/non-face classification using global threshold during face detection
142(1)
8.5.2 Comparison between threshold selections by ROC- based and set estimation-based techniques
142(1)
8.5.2.1 Formation of training-validation-test set
143(3)
8.6 Classification of face/non-face regions
146(2)
8.7 Class specific thresholds of face-class boundaries for face recognition
148(1)
8.8 Experimental design and result analysis
149(12)
8.8.1 Description of face dataset
149(2)
8.8.1.1 Recognition rates
151(1)
8.8.2 Open test results considering imposters in the system
151(2)
8.8.3 Recognition rates considering only clients in the system
153(8)
9 Evolutionary design for face recognition
161(10)
9.1 Introduction
161(1)
9.2 Genetic algorithms
162(3)
9.2.1 Implementation
163(1)
9.2.2 Algorithm
164(1)
9.3 Representation and discrimination
165(6)
9.3.1 Whitening and rotation transformation
165(2)
9.3.2 Chromosome representation and genetic operators
167(1)
9.3.3 The fitness function
167(1)
9.3.4 The evolutionary pursuit algorithm for face recognition
168(3)
10 Frequency domain correlation filters in face recognition
171(52)
10.1 Introduction
172(2)
10.1.1 PSR calculation
173(1)
10.2 A brief review on correlation filters
174(5)
10.3 Mathematical background of correlation filter
179(9)
10.3.1 ECPSDF filter design
179(2)
10.3.2 MACE filter design
181(1)
10.3.2.1 Constrained optimization with Lagrange multipliers
182(1)
10.3.3 MVSDF filter design
183(1)
10.3.4 Optimal trade-off (OTF) filter design
183(1)
10.3.5 Unconstrained correlation filter design
184(1)
10.3.5.1 MACH filter design
184(3)
10.3.5.2 UMACE filter design
187(1)
10.3.5.3 OTMACH filter design
188(1)
10.4 Physical requirements in designing correlation filters
188(2)
10.5 Applications of correlation filters
190(3)
10.6 Performance analysis
193(12)
10.6.1 Performance evaluation using PSR values
194(1)
10.6.2 Performance evaluation in terms of %RR and %FAR
195(9)
10.6.3 Performance evaluation by receiver operating characteristics (ROC) curves
204(1)
10.7 Video correlation filter
205(1)
10.8 Formulation of unconstrained video filter
206(6)
10.8.1 Mathematical formulation of MUOTSDF
207(2)
10.8.2 Unconstrained video filter
209(3)
10.9 Distance classifier correlation filter
212(1)
10.10 Application of UVF for face detection
213(10)
10.10.1 Training approach
213(1)
10.10.2 Testing approach
213(4)
10.10.3 Face detection in video using UVF
217(1)
10.10.3.1 Modification in training approach
218(1)
10.10.4 Validation of face detection
219(1)
10.10.5 Face classification using DCCF
219(4)
11 Subspace-based face recognition in frequency domain
223(30)
11.1 Introduction
224(1)
11.2 Subspace-based correlation filter
224(2)
11.3 Mathematical modelling with ID subspace
226(4)
11.3.1 Reconstructed correlation filter using ID subspace
226(2)
11.3.2 Optimum projecting image correlation filter using ID subspace
228(2)
11.4 Face classification and recognition analysis in frequency domain
230(1)
11.5 Test results with ID subspace analysis
231(2)
11.5.1 Comparative study in terms of PSRs
231(1)
11.5.2 Comparative study on %RR and %FAR
232(1)
11.6 Mathematical modelling with 2D subspace
233(3)
11.6.1 Reconstructed correlation filter using 2D subspace
234(2)
11.7 Test results on 2D subspace analysis
236(3)
11.7.1 PSR value distribution for authentic and impostor classes
236(1)
11.7.2 Comparative performance in terms of %RR
236(2)
11.7.3 Performance evaluation using ROC analysis
238(1)
11.8 Class-specific nonlinear correlation filter
239(1)
11.9 Formulation of nonlinear correlation filters
240(4)
11.9.1 Nonlinear optimum projecting image correlation filter
240(3)
11.9.2 Nonlinear optimum reconstructed image correlation filter
243(1)
11.10 Face recognition analysis using correlation classifiers
244(1)
11.11 Test results
245(8)
11.11.1 Comparative study on discriminating performances
245(1)
11.11.2 Comparative performance based on PSR distribution
246(2)
11.11.3 Performance analysis using ROC
248(2)
11.11.4 Noise sensitivity
250(3)
12 Landmark localization for face recognition
253(20)
12.1 Introduction
253(1)
12.2 Elastic bunch graph matching
253(1)
12.3 Gabor wavelets
254(3)
12.4 Gabor jets
257(2)
12.5 The elastic bunch graph matching algorithm
259(1)
12.6 Application to face recognition
260(1)
12.7 Facial landmark detection
261(2)
12.7.1 ASEF correlation filter
261(1)
12.7.2 Formulation of ASEF
262(1)
12.8 Eye detection
263(1)
12.9 Multicorrelation approach
264(4)
12.9.1 Design of landmark filter(LF)
264(3)
12.9.2 Landmark localization with localization filter
267(1)
12.10 Test results
268(5)
13 Two-dimensional synthetic face generation using set estimation
273(18)
13.1 Introduction
273(1)
13.2 Generating face points from intraclass face images
274(3)
13.2.1 Face generation using algorithm with intraclass features and related peak signal to noise ratio
274(3)
13.3 Generating face points from interclass face images
277(6)
13.3.1 Face generation with interclass features
280(3)
13.3.2 Rejection of the non-meaningful face and corresponding PSNR test
283(1)
13.4 Generalization capability of set estimation method
283(3)
13.5 Test of significance
286(5)
14 Datasets of face images for face recognition systems
291(12)
14.1 Face datasets
291(6)
14.1.1 ORL dataset
292(1)
14.1.2 OULU physics dataset
292(1)
14.1.3 XM2VTS dataset
293(1)
14.1.4 Yale dataset
293(1)
14.1.5 Yale-B dataset
294(1)
14.1.6 MIT dataset
294(1)
14.1.7 PIE dataset
295(1)
14.1.8 UMIST dataset
295(1)
14.1.9 PURDU AR dataset
295(1)
14.1.10 FERET dataset
296(1)
14.1.11 Performance evaluation of face recognition algorithms
296(1)
14.2 FERET and XM2VTS protocols
297(1)
14.3 Face recognition grand challenge (FRGC)
298(1)
14.4 Face recognition vendor test (FRVT)
299(1)
14.5 Multiple biometric grand challenge
300(1)
14.6 Focus of evaluation
301(2)
Conclusion 303(2)
Bibliography 305(18)
Index 323
Asit Kumar Datta is a former professor of the University of Calcutta (CU), Kolkata, India, where he served in the Department of Applied Physics and the Department of Applied Optics and Photonics. He holds an M.Tech and Ph.D from the same university. Dr. Datta spent 19 years as a professor and a total of 40 years of teaching and research at the post-graduate level at CU. In addition, he served for 8 years as a principal scientist/principal scientific officer of a CU research center in optical electronics. Widely published in international journals and conference proceedings, Dr. Datta has guided 14 scholars toward their Ph.Ds and has published nearly 125 papers. He has contributed significantly in the areas of photonic computation, photonic and electronic instrumentation, optical communications, and pattern recognition. He represented India at the International Commission on Optics and the International Commission on Illumination.

Madhura Datta is the assistant director of the University Grants Commission-Human Resources Development Center, University of Calcutta, Kolkata, India. She holds an M.Sc in computer and information science, and an M.Tech and Ph.D in computer science and engineering from the University of Calcutta. Her primary areas of research are face detection and recognition. Her work has been featured in various technical publications and conference proceedings, including the Journal of Pattern Recognition Research, Computer Vision and Image Understanding, International Journal of Pattern Recognition and Artificial Intelligence, International Conference on Pattern Recognition and Machine Intelligence, and IEEE International Conference on Intelligent Human Computer Interaction.

Pradipta Kumar Banerjee is an associate professor in the Department of Electrical Engineering of the Future Institute of Engineering and Management, Kolkata, India. He holds a B.Sc, B.Tech, M.Tech, and Ph.D from the
Püsilink: https://www.kriso.ee/db/9780429157196_pe.html