List of Contributors |
|
xvii | (4) |
Preface |
|
xxi | (2) |
Acknowledgments |
|
xxiii | (2) |
Introduction |
|
xxv | (10) |
Multimedia in the View of the Younger Generation |
|
xxxv | |
PART I MULTIMEDIA SYSTEMS, STANDARDS, AND TRENDS |
|
1 | (116) |
|
1 CURRENT AND FUTURE TRENDS IN MULTIMEDIA STANDARDS |
|
|
3 | (67) |
|
|
3 | (33) |
|
|
3 | (2) |
|
1.1.2 H.263: The ITU-T Low Bit-Rate Video Standard |
|
|
5 | (1) |
|
|
6 | (2) |
|
1.1.4 MPEG-4 Requirements |
|
|
8 | (3) |
|
|
11 | (11) |
|
|
22 | (1) |
|
1.1.7 MPEG-4 Syntax Description Language (MSDL) |
|
|
22 | (9) |
|
1.1.8 MPEG-4 Synthetic and Natural Hybrid Coding (SNHC) |
|
|
31 | (4) |
|
1.1.9 Summary and the Future |
|
|
35 | (1) |
|
1.2 Part II: Summary of DAVIC 1.0 Specification |
|
|
36 | (19) |
|
|
36 | (1) |
|
1.2.2 DAVIC Specification 1.0 |
|
|
37 | (16) |
|
|
53 | (2) |
|
1.3 Part III: Multimedia Standards for Network Applications |
|
|
55 | (13) |
|
|
55 | (5) |
|
|
60 | (5) |
|
|
65 | (3) |
|
|
68 | (2) |
|
2 MULTIMEDIA TECHNOLOGIES AND VLSI SYSTEMS |
|
|
70 | (24) |
|
2.1 Multimedia System and Technology Components |
|
|
70 | (4) |
|
2.2 Multimedia Transport and VLSI |
|
|
74 | (7) |
|
2.3 Multimedia Processing and VLSI |
|
|
81 | (3) |
|
2.4 Architectural Options |
|
|
84 | (4) |
|
|
84 | (1) |
|
2.4.2 Custom Data Path Engine |
|
|
85 | (2) |
|
2.4.3 Application-Specific Processing Engines |
|
|
87 | (1) |
|
|
88 | (1) |
|
|
89 | (3) |
|
|
92 | (1) |
|
|
92 | (2) |
|
3 INTRODUCTION TO RESEARCH ON MULTIMEDIA TECHNIQUES IN TELECOMMUNICATION LABORATORIES |
|
|
94 | (23) |
|
3.1 Development of Multimedia Telecommunication Services |
|
|
94 | (4) |
|
3.1.1 ISDN Distance Learning System |
|
|
94 | (2) |
|
3.1.2 Multimedia ISDN Teleshopping System |
|
|
96 | (2) |
|
3.2 ATM Broadband Experimental Network and Applications |
|
|
98 | (3) |
|
|
98 | (1) |
|
3.2.2 Services and Applications |
|
|
99 | (2) |
|
3.3 Intelligent Technology and Multimedia Applications |
|
|
101 | (11) |
|
3.3.1 Intelligent Pen-Based Input Technique |
|
|
101 | (2) |
|
3.3.2 Gin-Ih Chinese Character Recognition System |
|
|
103 | (1) |
|
3.3.3 Intelligent and Automatic Official Document Processing System |
|
|
103 | (2) |
|
3.3.4 Intelligent Computer Speech Synthesis System |
|
|
105 | (1) |
|
3.3.5 Intelligent Chinese Speech Recognition System |
|
|
106 | (1) |
|
3.3.6 Trademark and Commerical Logo Information Processing System |
|
|
107 | (1) |
|
3.3.7 Interactive Telecommunication Training System (ITTS) |
|
|
108 | (1) |
|
3.3.8 Video-on-Demand (VOD) Services |
|
|
109 | (1) |
|
3.3.9 IWDPS and Future Works |
|
|
110 | (2) |
|
3.4 Development of Multimedia Customer Systems |
|
|
112 | (2) |
|
3.4.1 PC-Based ISDN Terminal |
|
|
112 | (1) |
|
3.4.2 PC-Based ISDN Videophone System |
|
|
112 | (1) |
|
3.4.3 384K Videoconference System |
|
|
112 | (2) |
|
3.4.4 Single-Board PC-Based ISDN Videophone System |
|
|
114 | (1) |
|
|
114 | (1) |
|
|
114 | (3) |
PART II SUBMICRON ELECTRONIC TECHNOLOGIES |
|
117 | (98) |
|
4 MEMORY ARCHITECTURES TECHNOLOGY FOR MULTIMEDIA SYSTEMS |
|
|
119 | (37) |
|
4.1 Overview of the Semiconductor Memory Industry |
|
|
119 | (4) |
|
|
119 | (1) |
|
|
120 | (2) |
|
|
122 | (1) |
|
4.2 Key Elements for Memory |
|
|
123 | (6) |
|
|
124 | (5) |
|
|
129 | (1) |
|
4.3 Low-Power Design Technology |
|
|
129 | (8) |
|
4.3.1 Lowering Operating Voltage |
|
|
130 | (1) |
|
4.3.2 Charging Capacitance Reduction |
|
|
131 | (2) |
|
4.3.3 DC Leakage Current Reduction |
|
|
133 | (4) |
|
4.4 High-Throughput Technology |
|
|
137 | (17) |
|
|
138 | (1) |
|
4.4.2 Fast Page Mode DRAM |
|
|
139 | (3) |
|
4.4.3 Extended Data Out Mode (EDO) |
|
|
142 | (3) |
|
|
145 | (3) |
|
|
148 | (2) |
|
4.4.6 Ramlink and Synclink |
|
|
150 | (2) |
|
|
152 | (1) |
|
|
152 | (2) |
|
|
154 | (1) |
|
|
154 | (1) |
|
|
154 | (2) |
|
|
156 | (34) |
|
5.1 Part I: Single-Chip Multimedia Camera |
|
|
156 | (12) |
|
|
156 | (1) |
|
|
157 | (2) |
|
|
159 | (3) |
|
|
162 | (3) |
|
5.1.5 Back-End Manufacturing Steps |
|
|
165 | (2) |
|
5.1.6 Evolution of Single-Chip Cameras |
|
|
167 | (1) |
|
|
168 | (1) |
|
5.2 Part II: CMOS Image Sensor Technology |
|
|
168 | (15) |
|
|
169 | (1) |
|
5.2.2 Historical Background |
|
|
169 | (3) |
|
5.2.3 Overall Architecture |
|
|
172 | (1) |
|
|
173 | (7) |
|
5.2.5 Analog Signal Processing |
|
|
180 | (1) |
|
5.2.6 On-chip Analog-to-Digital Converter (ADC) |
|
|
180 | (1) |
|
5.2.7 Impact of CMOS Scaling Trends |
|
|
181 | (2) |
|
5.2.8 Roadmap for Camera-on-a-Chip |
|
|
183 | (1) |
|
|
183 | (1) |
|
|
184 | (1) |
|
|
184 | (6) |
|
6 CAD OF MULTIMEDIA SYSTEMS |
|
|
190 | (25) |
|
|
190 | (1) |
|
6.2 The CAD Environment: DSP Canvas |
|
|
191 | (3) |
|
6.2.1 The JetStream Data Flow Simulator |
|
|
191 | (1) |
|
6.2.2 SystemSolve: Iterative Simulation and Optimization Tool |
|
|
192 | (2) |
|
6.3 Using DSP Canvas to Design and Emulate a Multimedia, Wireless Communication System |
|
|
194 | (13) |
|
6.3.1 Video Coding Algorithm Design |
|
|
194 | (4) |
|
6.3.2 Speech Codec Design |
|
|
198 | (3) |
|
|
201 | (3) |
|
6.3.4 A Direct-Sequence Spread-Spectrum Modem Design |
|
|
204 | (3) |
|
6.4 Computer-Aided Implementation of Multimedia Communications Components |
|
|
207 | (5) |
|
|
212 | (1) |
|
|
212 | (1) |
|
|
213 | (2) |
PART III DIGITAL LIBRARY AND SERVICES |
|
215 | (132) |
|
7 THE TERADATA SQL3 MULTIMEDIA DATABASE SERVER |
|
|
217 | (36) |
|
7.1 The State of Client/Server Multimedia Applications |
|
|
217 | (2) |
|
7.2 Database Support for Multimedia Applications |
|
|
219 | (1) |
|
7.3 Programming a Multimedia Database System |
|
|
220 | (4) |
|
7.3.1 Defining New Multimedia Data Types |
|
|
220 | (2) |
|
7.3.2 Using These Data Types to Create Multimedia Tables |
|
|
222 | (1) |
|
7.3.3 Loading Multimedia Objects and Computing Feature Extracts |
|
|
222 | (1) |
|
7.3.4 Writing SQL Queries That Include Multimedia Terms |
|
|
223 | (1) |
|
7.4 Teradata Architecture for Multimedia Applications |
|
|
224 | (5) |
|
7.4.1 Federated Coordinator |
|
|
224 | (3) |
|
7.4.2 Relational Database Manager |
|
|
227 | (1) |
|
7.4.3 Multimedia Object Manager |
|
|
227 | (1) |
|
7.4.4 Real-Time Object Manager |
|
|
228 | (1) |
|
7.4.5 System Configuration Options |
|
|
228 | (1) |
|
7.5 Multimedia Object Manager Overview |
|
|
229 | (5) |
|
7.5.1 Multimedia Object Manager Design Principles |
|
|
230 | (1) |
|
7.5.2 Multimedia Object Manager Architecture |
|
|
230 | (1) |
|
|
230 | (2) |
|
7.5.4 Multimedia Object Storage Engine |
|
|
232 | (1) |
|
7.5.5 Multimedia Function (MMF) Library |
|
|
233 | (1) |
|
7.6 Content-Based Retrieval |
|
|
234 | (8) |
|
|
235 | (1) |
|
7.6.2 Querying on Features |
|
|
235 | (3) |
|
7.6.3 Acceleration of Queries Via Indices |
|
|
238 | (2) |
|
7.6.4 Teradata Architecture to Support Content Queries |
|
|
240 | (2) |
|
|
242 | (4) |
|
7.7.1 Multimodal Examples |
|
|
242 | (2) |
|
7.7.2 Multimodal Technical Challenges |
|
|
244 | (2) |
|
7.8 Talking Agents Example |
|
|
246 | (4) |
|
|
248 | (1) |
|
7.8.2 Talking Agent Generation |
|
|
249 | (1) |
|
|
250 | (1) |
|
|
250 | (1) |
|
|
251 | (2) |
|
8 VIDEO INDEXING AND RETRIEVAL |
|
|
253 | (29) |
|
|
253 | (3) |
|
8.2 Temporal Segmentation of Video Sequences |
|
|
256 | (4) |
|
8.3 Motion-based Indexing and Retrieval Methods |
|
|
260 | (1) |
|
8.4 Image-based Indexing and Retrieval Methods |
|
|
261 | (5) |
|
8.4.1 Global-scene-based Methods |
|
|
262 | (1) |
|
8.4.2 Object-based Methods |
|
|
263 | (3) |
|
8.5 Video Browsing System Using Human Faces |
|
|
266 | (6) |
|
8.5.1 Face Detection and Recognition |
|
|
267 | (3) |
|
8.5.2 Experimental Results |
|
|
270 | (2) |
|
8.6 Video Shot Classification Using Human Faces |
|
|
272 | (6) |
|
8.6.1 System Configuration of Video Classification |
|
|
273 | (1) |
|
8.6.2 Clustering of Facial Images |
|
|
274 | (4) |
|
|
278 | (1) |
|
|
279 | (1) |
|
|
279 | (3) |
|
9 CONTENT-BASED IMAGE RETRIEVAL--RESEARCH ISSUES |
|
|
282 | (41) |
|
|
282 | (4) |
|
9.2 Image Query by Content--The Challenge |
|
|
286 | (5) |
|
9.3 Fourier-Transform Techniques |
|
|
291 | (18) |
|
9.3.1 Convolution and Correlation Operations |
|
|
291 | (2) |
|
9.3.2 Frequency-domain Computation of Discrimination Functions |
|
|
293 | (11) |
|
9.3.3 Searching JPEG-and MPEG-encoded Images |
|
|
304 | (5) |
|
9.4 Wavelet Transform Techniques |
|
|
309 | (8) |
|
9.5 Architecture Support for Image Query |
|
|
317 | (3) |
|
9.6 Summary and Conclusions |
|
|
320 | (1) |
|
|
321 | (1) |
|
|
321 | (2) |
|
10 DATA STORAGE AND RETRIEVAL IN DISK-ARRAY-BASED VIDEO SERVERS |
|
|
323 | (24) |
|
|
323 | (3) |
|
10.2 Video Replication in Disk Arrays |
|
|
326 | (3) |
|
10.2.1 Conventional Data Placement |
|
|
326 | (1) |
|
10.2.2 Description of RMD Scheme |
|
|
327 | (2) |
|
10.3 Data Retrieval in a Disk |
|
|
329 | (2) |
|
10.4 Storing Scalable Video Data |
|
|
331 | (3) |
|
10.4.1 Rate Staggering for Scalable Video Data Storage |
|
|
332 | (1) |
|
10.4.2 Advantages of Rate Staggering |
|
|
333 | (1) |
|
10.5 Providing Pause/Resume Operations with Batching and Buffering |
|
|
334 | (1) |
|
10.6 Fast Forward and Fast Backward Functions |
|
|
335 | (5) |
|
10.6.1 MPEG Data Organization |
|
|
336 | (1) |
|
10.6.2 Segment Sampling Method |
|
|
337 | (1) |
|
10.6.3 Segment Placement Method |
|
|
338 | (2) |
|
10.7 Downloading: An Alternative to Real-Time Playout |
|
|
340 | (3) |
|
|
343 | (1) |
|
|
343 | (1) |
|
|
343 | (4) |
PART IV NETWORKING |
|
347 | (82) |
|
11 HIGH-SPEED LAN, MAN, AND ATM PROTOCOLS AS MULTIMEDIA CARRIERS |
|
|
349 | (41) |
|
|
349 | (1) |
|
11.2 Multimedia Traffic Characteristics and Quality-of-Service Requirements |
|
|
350 | (3) |
|
11.2.1 Q.S. Specification |
|
|
350 | (3) |
|
11.3 High-Speed LAN Protocols for Multimedia Transmission |
|
|
353 | (9) |
|
11.3.1 Options to Improve LAN Performance |
|
|
354 | (1) |
|
11.3.2 Enhanced Ethernet LAN Protocols |
|
|
354 | (3) |
|
11.3.3 Performance of Enhanced Ethernet Protocols |
|
|
357 | (5) |
|
11.4 High-Speed MAN Protocols for Multimedia Transmission |
|
|
362 | (13) |
|
11.4.1 Token-Based MAN Protocols: FDDI and FDDI-II |
|
|
363 | (1) |
|
11.4.2 Reservation-Based MAN Protocols: DQDB, CRMA, DQMA, and FDQ |
|
|
363 | (5) |
|
11.4.3 Throughput Performance |
|
|
368 | (2) |
|
|
370 | (5) |
|
|
375 | (10) |
|
11.5.1 ATM QoS and Service Classes |
|
|
375 | (1) |
|
11.5.2 ATM Traffic Control |
|
|
376 | (1) |
|
11.5.3 Rate-Based ABR Congestion Control Schemes |
|
|
377 | (2) |
|
11.5.4 Performance of ABR Congestion Control: The Effect of Bursty Source Traffic |
|
|
379 | (2) |
|
11.5.5 Burst-Level Admission Control Schemes |
|
|
381 | (2) |
|
11.5.6 Performance of FRP, AFRP, and MFRP |
|
|
383 | (2) |
|
11.6 Summary and Conclusions |
|
|
385 | (1) |
|
|
386 | (1) |
|
|
386 | (4) |
|
12 HIGH-SPEED OPTICAL INTERCONNECT FOR MULTIMEDIA SYSTEMS |
|
|
390 | (23) |
|
|
390 | (1) |
|
12.2 Existing Interconnection Hierarchy |
|
|
391 | (3) |
|
|
393 | (1) |
|
|
393 | (1) |
|
12.2.3 Crosstalk Among Adjacent Interconnects |
|
|
394 | (1) |
|
12.2.4 Frequency-dependent Signal Distortion |
|
|
394 | (1) |
|
12.3 Optical Interconnects |
|
|
394 | (3) |
|
12.3.1 Potential Advantages |
|
|
395 | (1) |
|
12.3.2 Potential Problems |
|
|
395 | (2) |
|
12.4 Architecture of Optical Interconnects |
|
|
397 | (6) |
|
12.4.1 Interconnect Media |
|
|
398 | (1) |
|
12.4.2 Backplane Optical Interconnects |
|
|
399 | (1) |
|
12.4.3 Board and Multichip-Module Optical Interconnects |
|
|
399 | (3) |
|
12.4.4 Fully Differential Optical Interconnect |
|
|
402 | (1) |
|
12.5 Technologies for Optical Interconnect Systems |
|
|
403 | (2) |
|
|
403 | (1) |
|
|
403 | (2) |
|
|
405 | (1) |
|
12.6 Research Activities on Optical Interconnects |
|
|
405 | (1) |
|
|
406 | (1) |
|
|
407 | (6) |
|
13 NETWORKS FOR THE PROFESSIONAL CAMPUS ENVIRONMENT |
|
|
413 | (16) |
|
|
413 | (2) |
|
13.2 Advanced Fiber-Optic Physical Layer Technologies |
|
|
415 | (2) |
|
13.3 High-Performance Network Interfaces |
|
|
417 | (3) |
|
13.4 New Protocols for Low-Latency and High Sustained Throughput |
|
|
420 | (3) |
|
13.5 The Need for Vertical Integration from Physical Layers to Application Interfaces |
|
|
423 | (3) |
|
|
426 | (1) |
|
|
426 | (1) |
|
|
426 | (3) |
PART V MULTIMEDIA SIGNAL PROCESSING AND APPLICATIONS |
|
429 | (226) |
|
14 INTELLIGENT SPEECH/AUDIO PROCESSING FOR MULTIMEDIA APPLICATIONS |
|
|
431 | (32) |
|
|
431 | (2) |
|
14.2 Speech/Audio Compression |
|
|
433 | (6) |
|
14.2.1 Low Bit-Rate Speech Coding |
|
|
433 | (2) |
|
14.2.2 High-Fidelity Audio Coding |
|
|
435 | (2) |
|
14.2.3 Industrial Standards and Applications |
|
|
437 | (2) |
|
14.3 Text-to-Speech Conversion |
|
|
439 | (4) |
|
14.3.1 Text-to-Speech Synthesis |
|
|
440 | (3) |
|
14.3.2 Text-to-Speech Technology for Multimedia |
|
|
443 | (1) |
|
14.4 Speech Understanding |
|
|
443 | (6) |
|
14.4.1 Automatic Speech Recognition |
|
|
443 | (3) |
|
14.4.2 Speaker Recognition |
|
|
446 | (1) |
|
14.4.3 Applications of Speech Understanding for Multimedia |
|
|
447 | (2) |
|
|
449 | (2) |
|
14.5.1 Representation of Music |
|
|
450 | (1) |
|
14.5.2 Computer Music for Multimedia |
|
|
450 | (1) |
|
14.6 VLSI Design for Speech/Audio Processing |
|
|
451 | (7) |
|
14.6.1 VLSI Speech/Audio Processors |
|
|
453 | (4) |
|
14.6.2 Commercial Hardware Products |
|
|
457 | (1) |
|
|
458 | (1) |
|
|
458 | (1) |
|
|
459 | (4) |
|
15 SPEECH RECOGNITION IN MULTIMEDIA HUMAN-MACHINE INTERFACES USING NEURAL NETWORKS |
|
|
463 | (27) |
|
|
463 | (3) |
|
15.1.1 Motivation and Applications of Speech Recognition to Multimedia Systems |
|
|
463 | (1) |
|
15.1.2 Current State and Related Problems in Mandarin Speech Recognition |
|
|
464 | (1) |
|
15.1.3 The Potential of Neural Networks for Mandarin Speech Recognition |
|
|
465 | (1) |
|
15.2 Neural Networks for Isolated Mandarin Speech Recognition |
|
|
466 | (5) |
|
15.2.1 The Acoustic Signal Processor |
|
|
466 | (2) |
|
15.2.2 The Language Processing Model |
|
|
468 | (3) |
|
15.3 Continuous Mandarin Speech Recognition Based on Neural Networks |
|
|
471 | (11) |
|
15.3.1 Segmenting Recognizer for Continuous Speech |
|
|
471 | (3) |
|
15.3.2 Nonsegmenting DTW Recognizer Using Neural Networks |
|
|
474 | (4) |
|
15.3.3 Keyword Spotting Using Neural Networks |
|
|
478 | (4) |
|
15.4 VenusDictate: A Robust and Practical Mandarin Speech Recognition System for Multimedia Applications |
|
|
482 | (4) |
|
15.4.1 Introduction to VenusDictate System |
|
|
482 | (1) |
|
15.4.2 System Description |
|
|
482 | (3) |
|
15.4.3 Applications to Multimedia Systems |
|
|
485 | (1) |
|
15.5 Future Trends and Conclusions |
|
|
486 | (1) |
|
|
486 | (4) |
|
16 HANDWRITTEN RECOGNITION FOR THE MULTIMEDIA HUMAN-MACHINE INTERFACE |
|
|
490 | (37) |
|
|
490 | (2) |
|
16.1.1 Motivation and Applications of Handwritten Recognition to Multimedia Systems |
|
|
491 | (1) |
|
16.1.2 Current Status and Related Problems in Handwritten Recognition |
|
|
491 | (1) |
|
16.2 Techniques for Handwritten Recognition |
|
|
492 | (21) |
|
16.2.1 Overview of Handwritten Recognition |
|
|
492 | (3) |
|
16.2.2 Handwritten English and Numerical Character Recognition |
|
|
495 | (5) |
|
16.2.3 Handwritten Chinese Character Recognition |
|
|
500 | (7) |
|
16.2.4 On-Line Handwritten Recognition |
|
|
507 | (3) |
|
16.2.5 Source of Information on Handwritten Recognition |
|
|
510 | (3) |
|
16.3 Handwritten Recognition Systems |
|
|
513 | (7) |
|
16.3.1 CCL FR1000 Form Processing System |
|
|
513 | (4) |
|
16.3.2 NeuroScan II: A Handwritten Chinese Character Recognizer |
|
|
517 | (2) |
|
16.3.3 Pen Power OLCCR Systems |
|
|
519 | (1) |
|
16.4 Future Trends and Conclusions |
|
|
520 | (1) |
|
|
521 | (1) |
|
|
521 | (6) |
|
17 HARDWARE DESIGN FOR 3-D GRAPHICS |
|
|
527 | (40) |
|
|
527 | (8) |
|
17.1.1 Goal of the 3-D Graphics Processor |
|
|
528 | (1) |
|
17.1.2 Methods for Rendering 3-D Graphics |
|
|
529 | (6) |
|
17.2 3-D Graphics Hardware Architecture |
|
|
535 | (14) |
|
17.2.1 Standard 3-D Graphics Rendering Pipeline |
|
|
535 | (2) |
|
17.2.2 The Bottlenecks of 3-D Graphics Rendering |
|
|
537 | (3) |
|
17.2.3 Techniques for 3-D Graphics Hardware |
|
|
540 | (9) |
|
17.3 3-D Graphics Processors |
|
|
549 | (11) |
|
17.3.1 Geometric Subsystem |
|
|
549 | (2) |
|
|
551 | (6) |
|
17.3.3 Overall Graphics System |
|
|
557 | (3) |
|
17.4 The 3-D Graphics Application Program Interface |
|
|
560 | (3) |
|
17.4.1 Window-independent 3-D API |
|
|
560 | (2) |
|
17.4.2 Window-dependent 3-D API |
|
|
562 | (1) |
|
|
563 | (1) |
|
|
564 | (1) |
|
|
564 | (3) |
|
18 VIRTUAL WORLDS AS FUZZY DYNAMICAL SYSTEMS |
|
|
567 | (37) |
|
18.1 Fuzzy Virtual Worlds |
|
|
567 | (1) |
|
18.2 Additive Fuzzy Systems |
|
|
568 | (7) |
|
18.3 Fuzzy Cognitive Maps |
|
|
575 | (7) |
|
|
577 | (1) |
|
|
578 | (1) |
|
|
579 | (2) |
|
|
581 | (1) |
|
18.4 Virtual Undersea World |
|
|
582 | (9) |
|
18.4.1 Augmented Virtual World |
|
|
585 | (3) |
|
18.4.2 Nested FCMs for Fish Schools |
|
|
588 | (3) |
|
18.5 Adaptive Fuzzy Cognitive Maps |
|
|
591 | (5) |
|
|
596 | (1) |
|
|
597 | (2) |
|
Appendix A Proof of the Fuzzy Approximation Theorem |
|
|
599 | (1) |
|
Appendix B Learning in SAMs: Unsupervised Clustering and Supervised Gradient Descent |
|
|
600 | (4) |
|
19 MULTIMEDIA VISUAL TELEPHONE SYSTEM |
|
|
604 | (25) |
|
|
604 | (4) |
|
19.1.1 Why Multimedia Communication |
|
|
604 | (2) |
|
19.1.2 The MPEG-4 Standard |
|
|
606 | (1) |
|
19.1.3 H.263: Video Coding Standard for the Visual Telephone System |
|
|
607 | (1) |
|
19.2 System Configuration for the Multimedia Visual Telephone |
|
|
608 | (5) |
|
19.2.1 Overview of the System |
|
|
608 | (2) |
|
19.2.2 H.263: Video Codec |
|
|
610 | (2) |
|
19.2.3 G.723: Speech Codec |
|
|
612 | (1) |
|
19.3 Video Coding Algorithms for the System |
|
|
613 | (11) |
|
|
613 | (2) |
|
19.3.2 Unrestricted Motion Vectors Mode |
|
|
615 | (1) |
|
19.3.3 Syntax-based Arithmetic Coding Mode |
|
|
616 | (1) |
|
19.3.4 Advanced Prediction Mode |
|
|
617 | (5) |
|
|
622 | (2) |
|
19.4 Performance Evaluation |
|
|
624 | (2) |
|
19.4.1 Complexity and Bottleneck |
|
|
624 | (1) |
|
|
624 | (1) |
|
|
625 | (1) |
|
|
626 | (1) |
|
|
627 | (2) |
|
20 ADVANCED TECHNIQUES IN AUDIO-VISUAL INTERACTION |
|
|
629 | (26) |
|
|
629 | (2) |
|
20.1.1 Audiovisual Interaction |
|
|
629 | (1) |
|
20.1.2 Bimodal Speech Production and Perception |
|
|
630 | (1) |
|
20.1.3 Phonemes and Visemes |
|
|
630 | (1) |
|
20.2 Media Conversion: Auditory and Visual Speech |
|
|
631 | (2) |
|
20.2.1 From Visual to Audio: Automatic Lipreading |
|
|
632 | (1) |
|
20.2.2 From Audio to Visual: Speech-Driven Face Animation |
|
|
632 | (1) |
|
|
633 | (3) |
|
20.3.1 Automatic Dialog Synchronization |
|
|
633 | (1) |
|
20.3.2 Speech-Assisted Video Processing |
|
|
634 | (2) |
|
20.3.3 Dubbing of Films and Language Translation |
|
|
636 | (1) |
|
20.4 Image Analysis and Synthesis Techniques |
|
|
636 | (9) |
|
20.4.1 Image Analysis: Lipreading |
|
|
636 | (5) |
|
20.4.2 Image Synthesis: Facial Animation |
|
|
641 | (2) |
|
20.4.3 An Example Lip-Tracking System |
|
|
643 | (2) |
|
20.5 Joint Audio-Video Processing |
|
|
645 | (4) |
|
20.5.1 Cross-Modal Predictive Coding |
|
|
645 | (3) |
|
20.5.2 Speech-Assisted Motion Compensation |
|
|
648 | (1) |
|
20.5.3 Bimodal Person Authentication/Identification |
|
|
648 | (1) |
|
|
649 | (1) |
|
|
650 | (5) |
Index |
|
655 | (12) |
About the Editors |
|
667 | |