Atnaujinkite slapukų nuostatas

El. knyga: Unimodal and Multimodal Biometric Data Indexing [De Gruyter E-books]

,
  • Formatas: 357 pages, 7 Illustrations, black and white; 43 Tables, black and white; 3 Illustrations, color; color line drawings; b/w line drawings
  • Išleidimo metai: 28-Apr-2014
  • Leidėjas: De Gruyter
  • ISBN-13: 9781614516293
Kitos knygos pagal šią temą:
  • De Gruyter E-books
  • Kaina: 83,94 €*
  • * this price gives unlimited concurrent access for unlimited time
Unimodal and Multimodal Biometric Data IndexingDidesnis paveikslėlis
  • Formatas: 357 pages, 7 Illustrations, black and white; 43 Tables, black and white; 3 Illustrations, color; color line drawings; b/w line drawings
  • Išleidimo metai: 28-Apr-2014
  • Leidėjas: De Gruyter
  • ISBN-13: 9781614516293
Kitos knygos pagal šią temą:
Wiley OnlineMore info about De Gruyter e-books
Partnerių interneto svetainė: http://dx.doi.org/10.1515/9781614516293
Day and Samanta survey different biometrics data indexing methods that can be used in large-scale biometric personal identification systems that can accomplish matching processes in real-time without compromising the accuracy of the identification system. They consider the pros and cons of the different biometric traits, discuss different multimodal fusion strategies, introduce unimodal and multimodal biometric indexing methods, and review the fundamentals of biometric technologies. The traits they explain how to generate index keys from iris, fingerprint and face biometric and for multimodal indexing system. Annotation ©2015 Ringgold, Inc., Portland, OR (protoview.com)
Preface i
List of Figures ix
List of Tables xix
1 Fundamentals of Biometric Technology 1(32)
1.1 Biometric Authentication Technology
1(1)
1.2 Some Major Biometric Applications
2(2)
1.3 Operational Process of Biometric Technology
4(3)
1.4 Biometric Data Indexing
7(1)
1.5 Metrics for Performance Measure
7(1)
1.6 Biometric Modalities
8(5)
1.6.1 Iris Biometric
9(1)
1.6.2 Fingerprint Biometric
9(1)
1.6.3 Face Biometric
9(1)
1.6.4 Palmprint Biometric
10(1)
1.6.5 Hand Geometry Biometric
10(1)
1.6.6 Voice Biometric
11(1)
1.6.7 Gait Biometric
12(1)
1.6.8 Signature Biometric
12(1)
1.7 Comparative Study of Different Biometric Modalities
13(8)
1.7.1 Identification of Parameters
13(1)
1.7.2 Estimation of Values of Parameters
14(1)
1.7.3 Estimation of Impact Value
15(6)
1.7.4 Quantitative Comparison
21(1)
1.8 Summary
21(12)
2 Multimodal Biometric and Fusion Technology 33(46)
2.1 Multimodal Biometric Authentication Technology
33(1)
2.2 Fusion of Multimodalities
34(2)
2.3 Fusion Levels
36(6)
2.3.1 Sensor Level Fusion
36(2)
2.3.2 Feature Level Fusion
38(2)
2.3.3 Match-score Level Fusion
40(1)
2.3.4 Decision Level Fusion
41(1)
2.4 Different Fusion Rules
42(20)
2.4.1 Fixed fusion rules
42(3)
2.4.2 Trained Fusion Rules
45(17)
2.5 Comparative Study of Fusion Rule
62(6)
2.6 Summary
68(11)
3 Biometric Indexing: State-of-the-Art 79(32)
3.1 Survey on Iris Biometric Data Indexing
79(4)
3.1.1 Iris Texture-Based Indexing
80(2)
3.1.2 Iris Color-Based Indexing
82(1)
3.2 Survey on Fingerprint Biometric Data Indexing
83(11)
3.2.1 Minutiae-Based Indexing
85(3)
3.2.2 Ridge Orientation-Based Indexing
88(4)
3.2.3 Other Feature-Based Indexing Techniques
92(2)
3.3 Survey on Face Biometric Data Indexing
94(1)
3.4 Survey on Multimodal Biometric Data Indexing
95(2)
3.5 Summary
97(14)
4 Iris Biometric Data Indexing 111(38)
4.1 Preliminaries of Gabor Filter
112(3)
4.2 Preprocessing
115(2)
4.3 Feature Extraction
117(1)
4.4 Index Key Generation
118(1)
4.5 Storing
119(5)
4.5.1 Index Space Creation
119(1)
4.5.2 Storing Iris Data
120(4)
4.6 Retrieving
124(3)
4.7 Performance Evaluation
127(14)
4.7.1 Performance Metrics
128(2)
4.7.2 Databases
130(1)
4.7.3 Evaluation Setup
131(1)
4.7.4 Validation of the Parameter Values
132(2)
4.7.5 Evaluation
134(7)
4.8 Comparison with Existing Work
141(2)
4.9 Summary
143(6)
5 Fingerprint Biometric Data Indexing 149(56)
5.1 Preprocessing
150(7)
5.1.1 Normalization
150(1)
5.1.2 Segmentation
151(1)
5.1.3 Local Orientation Estimation
152(1)
5.1.4 Local Frequency Image Representation
152(1)
5.1.5 Ridge Filtering
153(1)
5.1.6 Binarization and Thinning
154(1)
5.1.7 Minutiae Point Extraction
154(3)
5.2 Feature Extraction
157(3)
5.2.1 Two Closest Points Triangulation
157(1)
5.2.2 Triplet Generation
158(2)
5.3 Index Key Generation
160(3)
5.4 Storing
163(10)
5.4.1 Linear Index Space
164(1)
5.4.2 Clustered Index Space
165(3)
5.4.3 Clustered kd-tree Index Space
168(5)
5.5 Retrieving
173(5)
5.5.1 Linear Search (LS)
174(1)
5.5.2 Clustered Search (CS)
175(2)
5.5.3 Clustered kd-tree Search (CKS)
177(1)
5.6 Performance Evaluation
178(17)
5.6.1 Databases
178(3)
5.6.2 Evaluation Setup
181(1)
5.6.3 Evaluation
182(10)
5.6.4 Searching Time
192(3)
5.6.5 Memory Requirements
195(1)
5.7 Comparison with Existing Work
195(4)
5.8 Summary
199(6)
6 Face Biometric Data Indexing 205(52)
6.1 Preprocessing
206(4)
6.1.1 Geometric Normalization
206(2)
6.1.2 Face Masking
208(1)
6.1.3 Intensity Enhancement
209(1)
6.2 Feature Extraction
210(8)
6.2.1 Key Point Detection
211(4)
6.2.2 Orientation Assignment
215(2)
6.2.3 Key Point Descriptor Extraction
217(1)
6.3 Index Key Generation
218(2)
6.4 Storing
220(5)
6.4.1 Index Space Creation
220(3)
6.4.2 Linear Storing Structure
223(1)
6.4.3 Kd-tree Storing Structure
223(2)
6.5 Retrieving
225(7)
6.5.1 Linear Search
228(2)
6.5.2 Kd-tree Search
230(2)
6.6 Performance Evaluation
232(19)
6.6.1 Database
232(2)
6.6.2 Evaluation Setup
234(3)
6.6.3 Validation of the Parameter Value
237(2)
6.6.4 Evaluation
239(12)
6.7 Comparison with Existing Work
251(1)
6.8 Summary
252(5)
7 Multimodal Biometric Data Indexing 257(48)
7.1 Feature Extraction
259(2)
7.2 Score Calculation
261(1)
7.3 Reference Subject Selection
262(4)
7.3.1 Sample Selection
262(2)
7.3.2 Subject Selection
264(2)
7.4 Reference Score Calculation
266(1)
7.5 Score Level Fusion
267(3)
7.5.1 Score Normalization
267(1)
7.5.2 Score Fusion
268(2)
7.6 Index Key Generation
270(2)
7.7 Storing
272(3)
7.7.1 Index Space Creation
272(1)
7.7.2 Storing Multimodal Biometric Data
273(2)
7.8 Retrieving
275(3)
7.9 Rank Level Fusion
278(4)
7.9.1 Creating Feature Vector for Ranking
279(1)
7.9.2 SVM Ranking
279(3)
7.10 Performance Evaluation
282(14)
7.10.1 Database
282(3)
7.10.2 Evaluation Setup
285(1)
7.10.3 Training of SVM-based Score Fusion Module
286(1)
7.10.4 Training of SVM-based Ranking Module
286(1)
7.10.5 Validation of the Parameter Values
287(3)
7.10.6 Evaluation
290(6)
7.11 Comparison with Existing Work
296(2)
7.12 Summary
298(7)
8 Conclusions and Future Research 305(18)
8.1 Dimensionality of Index Key Vector
305(3)
8.2 Storing and Retrieving
308(2)
8.3 Performance of Indexing Techniques
310(2)
8.4 Threats to Validity
312(3)
8.4.1 Internal Validity
312(2)
8.4.2 External Validity
314(1)
8.4.3 Construct Validity
314(1)
8.5 Future Scope of Work
315(8)
Index 323
Somnath Dey, Indian Institute of Technology, Indore, India; Debasis Samanta, Indian Institute of Technology, Kharagpur, India.
Pastovi nuoroda: https://www.kriso.lt/db/9781614516293_pe.html