Advances in Image Processing & Understanding : A Festschrift for Thomas S Huang.
Title:
Advances in Image Processing & Understanding : A Festschrift for Thomas S Huang.
Author:
Bovik, Alan C.
ISBN:
9789812776952
Personal Author:
Physical Description:
1 online resource (398 pages)
Series:
Series in Machine Perception and Artificial Intelligence ; v.52
Series in Machine Perception and Artificial Intelligence
Contents:
Contents -- Developmental Vision Audition Robots and Beyond -- 1.1 Introduction -- 1.1.1 The traditional manual development paradigm -- 1.1.2 Is human vision system totally genetically predetermined ? -- 1.1.3 The new autonomous development paradigm -- 1.1.4 The developmental approach -- 1.1.5 Comparison of approaches -- 1.1.6 More tractable -- 1.2 The SAIL-2 developmental program -- 1.2.1 Mode of operation: AA-learning -- 1.2.2 SAIL-2 developmental architecture -- 1.2.3 Sensory vector representation -- 1.2.4 Working memory and long-term memory -- 1.2.5 Innate and learned behaviors -- 1.3 The Mapping Engine: IHDR -- 1.3.1 Regression -- 1.3.2 Clustering in both input and output space -- 1.3.3 IHDR procedure -- 1.3.4 Amnesic average -- 1.3.5 Discriminating subspace -- 1.3.6 The probability-based metric -- 1.3.7 The transition among different likelihoods -- 1.3.8 Computational considerations -- 1.4 Experiments -- 1.4.1 SAIL robot -- 1.4.2 Autonomous navigation -- 1.4.3 Visual attention using motion -- 1.4.4 Test for the developmental algorithm SAIL-2 -- 1.4.5 Speech recognition -- 1.5 Conclusions -- Acknowledgements -- Bibliography -- A Piecewise Bezier Volume Deformation Model and Its Applications in Facial Motion Capture -- 1.Introduction -- 2 The PBVD model -- 2.1 PBVD -formulation and properties -- 2.2 PBVD-based facial animation -- 3 PBVD model-based tracking algorithm -- 3.1 Video analysis of the facial movements -- 3.2 Model-based tracking using the PBVD model -- 3 3 Coarse-to-fine framework -- 3.4 Confidence measurements -- 4 Explanation-based motion tracking -- 4.1 Approach -- 4.2 Learning expressions/visemes or action units -- 5 Implementation and experimental results -- 5.1 Face model initialization -- 5.2 PBVD model-based tracking -- 5.3 Explanation-based tracking -- 6 Discussion -- 7 Acknowledgements -- References.
Nonrigid Motion and Structure Analysis from 2D with Application Towards 3D Cloud Tracking -- 1. Introduction -- 2. Motivation and Previous Work -- 3. GOES Cloud Image Sequences -- 4. System Outline -- 5. Local Nonrigid Motion Model -- 5.1. Formulations -- 5.2. The Affine Motion Model and Cloud Fluid dynamics -- 6. Local Motion Model Fitting -- 6.1. Minimization Method and Error-of-Fit Function -- 6.2. Initial Guesses and Initial Depth Assumption -- 6.3. Depth Constraints -- 7. Global Constraints -- 7.1. Smooth Motion Assumption -- 7.2. Fluid Dynamics -- 7.3. Incorporating the Global Constraints -- 8 Experimental Results -- 9. Validations -- 10. Conclusions and Future Work -- References -- Map Structure Recognition and Automatic Map Data Acquisition -- 1. Introduction -- 2. System Framework -- 3. Pixel-Level Processing -- 3.1. Preprocessing -- 3.2. Map Image Thinning -- 4. Graph Representations of Maps -- 4.1. Graph Conversion -- 4.2. Graph Redundancy and Redundancy Elimination -- 4.3. Super Graph Description -- 5. Map Graph Segmentation and Re-linking -- 6. Rolling Ball: Road Structure Vectorization -- 6.1. Rolling ball method -- 6.2. Road Inter-Junction Detection -- 6.3. Road Network Exploration -- 7. House Data Generation -- 7.1. Recognize House Structures -- 7.2. House Data Vectorization -- 8. Discussion -- Reference -- Learning Visual Concepts for Content Based Retrieval -- 1. Introduction -- 2. Learning Visual Concepts -- 2.1. Feature Selection -- 2.2. Dynamic Feature Sets -- 3. Discussion -- 3.1. Major Challenges -- 3.2. Capability for Learning -- 4. Summary -- References -- Automated Human Facial Feature Extraction Using Double Resolution Pyramid -- Introduction to Human Facial Feature Extraction -- Overview of Automated Facial Feature Extraction Algorithm -- Multi-resolutional Face Templates.
Choosing face template -- Template consolidation -- Subtemplates for facial features -- Resolution pyramid of face image -- Similarity measures -- Search strategies -- Face Detection by Coarse-to-fine Multi-resolution Searching -- Feature Extraction by Global-to-local Matching -- Feedback Process -- Experiments -- Locating face area -- Matching with facial features -- Combining features extracted from different face views -- Results and Conclusions -- References -- Learning Based Relevance Feedback in Image Retrieval -- 1. Introduction -- 2. Concepts and Notations -- 3. Related Work -- 3.1. The MARS approach -- 3.2. The MindReader approach -- 3.2.1. Discussions -- 4. The Proposed Approach -- 4.1. Problem formulation -- 4.2. Optimal solution for qi -- 4.3. Optimal solution for Wi -- 4.4. Optimal Solution for u -- 5. Experiments Results and Evaluations -- 5.1. Data set -- 5.2. Queries -- 5.3. Visual features -- 5.4. Performance measures -- 5.5. System description -- 5.6. Results and observations -- 6. Discussions and Conclusions -- 7. Acknowledgment -- References -- Object-Based Subband/Wavelet Video Compression -- 1 Introduction -- 2 Joint Motion Estimation and Segmentation -- 2.1 Problem formulation -- 2.2 Probability models -- 2.3 Solution -- 2.4 Results -- 3 Parametric Representation of Dense Object Motion Field -- 3.1 Parametric motion of objects -- 3.2 Appearance of new regions -- 3.3 Coding the object boundaries -- 4 Object Interior Coding -- 4.1 Adaptive Motion-Compensated Coding -- 4-2 Spatiotemporal (3-D) Coding of Objects -- 5 Simulation results -- 6 Conclusions -- 7 References -- A Computational Approach to Semantic Event Detection in Video -- 1. Introduction -- 2. Methodology -- 2.1. Global Motion Estimation and Motion Blob Detection -- 2.2. Texture and Color Analysis -- 2.2.1. Gabor Filter Measures.
2.2.2. Graylevel Co-occurrence Matrix Measures -- 2.2.3. Fractal Dimension Measures -- 2.2.4. Color Measures -- 2.3. Region Classification and Motion Blob Verification -- 2.4. Shot Summarization -- 2.5. Event Inference -- 3. Experimental Results -- 3.1. Global Motion Estimation -- 3.2. Motion Blob Detection -- 3.3. Region Classification -- 3.4. Shot Summarization -- 3.5. Event Inference and Final Detection Results -- 3.5.1. Hunt Events -- 3.5.2. Landing Events -- 3.5.3 Rocket Launch Events -- 4. Summary and Discussion -- References -- Robust Video Transmission for Feedback Channels -- 10.1 Introduction -- 10.2 TRIRF-frame Coding -- 10.2.1 Construction of the TRIRF-frame -- 10.2.2 Multi-Mode Coding -- 10.3 Video Stream Packetization -- 10.3.1 Basic Considerations -- 10.3.2 Packet Header Specification -- 10.4 Coding Performance Comparisons -- 10.5 Efficiency Analysis of TRIRF Coding -- 10.5.1 Error-Free Analysis -- 10.5.1.1 Problem formulation -- 10.5.1.2 Rate computation for prediction errors -- 10.5.1.3 Rate computation for motion vectors -- 10.5.1.4 Rate derivation based on block motion -- 10.5.2 TRIRF Coding: Channels with Error -- 10.5.3 Simulations -- 10.5.3.1 Results for Reliable Channels -- 10.5.3.2 Results with Packet Errors -- 10.6 Conclusions -- Bibliography -- Multidimensional AM-FM Models with Image Processing Applications -- Preliminary Comments -- 1 Fundamentals of 2D AM-FM Modeling -- 2 Isolating the Multiple Image Components -- 3 AM-FM Demodulation -- 4 AM-FM Image Segmentation -- 5 AM-FM Reaction-Diffusion for Texture Completion -- 6 Multidimensional Orthogonal FM Transforms -- 7 Concluding Remarks -- 8 Acknowledgement -- References -- Image Transmission Over Noisy Channels: TCQ-Based Coding Schemes -- 1. Introduction -- 2. The Basic Algorithm With UTTCQ -- 2.1. System Description -- 2.2. Fixed-rate UTTCQ.
2.3. Bit Allocation Scheme -- 3. Nonuniform Threshold TCQ -- 4. UTTCQ With Block Classification -- 4.1. Description of the Enhanced Scheme -- 4.2. Classification Methods -- 4.3. Noise Reduction Filters -- 5. Layered Transmission with RCPC Channel Coding -- 5.1. Layered Grouping and RCPC coding -- 6. Experimental Results and Comparisons -- 7. Conclusion and Discussion -- Acknowledgements -- References -- Motion and Structure from Feature Correspondences: A Review -- I. INTRODUCTION -- II. GENERAL PROBLEM AND NOTATION -- III. 3D-TO-3D CORRESPONDENCES -- IV. 2D-TO-3D CORRESPONDENCES -- V. 2D-TO-2D CORRESPONDENCES -- VI. FUTURE RESEARCH AND OPEN QUESTIONS -- VII. SUMMARY AND CONCLUSION -- REFERENCES -- Toward Multimodal Human-Computer Interface -- I. INTRODUCTION -- II. WHY MULTIPLE MODALITIES IN HCI? -- III. MODALITIES FOR HCI -- IV. WHEN TO INTEGRATE THE HCI MODALITIES -- V. HOW TO INTEGRATE THE HCI MODALITIES -- VI. MULTIMODAL HCI SYSTEMS AND APPLICATIONS -- VII. DISCUSSION -- VIII. CONCLUDING REMARKS -- REFERENCES -- Image Processing -- I. INTRODUCTION -- II. IMAGE ENHANCEMENT -- III. EFFICIENT PICTURE CODING -- IV. OPTICAL IMAGE PROCESSING TECHNIQUES -- V. DIGITAL COMPUTER IMAGE PROCESSING TECHNIQUES -- VI. ELECTROOPTICAL DEVICES -- VII. IMAGE DESCRIPTION -- VIII. IMAGE QUALITY -- IX. CONCLUDING REMARKS -- BIBLIOGRAPHY -- REFERENCES.
Abstract:
This volume of original papers has been assembled to honor the achievements of Professor Thomas S Huang in the area of image processing and image analysis. Professor Huang's life of inquiry has spanned a number of decades as his work on imaging problems began in 1960's. Over these 40 years, he has made many fundamental and pioneering contributions to nearly every area of this field. Professor Huang has received numerous Awards, including the prestigious Jack Kilby Signal Processing Medal from IEEE. He has been elected to the National Academy of Engineering, and named Fellow of IEEE, Fellow of OSA, Fellow of IAPR, and Fellow of SPIE. Professor Huang has made fundamental contributions to image processing, pattern recognition, and computer vision: including design and stability test of multidimensional digital filters, digital holography; compression techniques for documents and images; 3D motion and modeling, analysis and visualization of the human face, hand and body, multi-modal human-computer interfaces; and multimedia databases. Many of his research ideas have been seminal, opening up new areas of research. Professor Huang is continuing his contribution to the field in the new millennium!. This book is intended to highlight his contributions by showing the breadth of areas in which his students are working. As such, contributed chapters were written by some of his many former graduate students (some with Professor Huang as a coauthor) and illustrate not only his contributions to imaging science but also his commitment to educational endeavor. The breadth of contributions is an indication of influence of Professor Huang to the field of signal processing, image processing, computer vision and applications; the book includes chapters on learning in image retrieval, facial motion analysis, cloud motion tracking, wavelet coding, robust video
transmission, and many other topics. The Appendix contains several reprints of Professor Huang's most influential papers from 1970's to 1990's. This book is directed towards image processing researchers, including academic faculty, graduate students and industry researchers, as well as toward professionals working in application areas. Contents: Developmental Vision, Audition, Robots and Beyond (J Weng et al.); A Piecewise Bézier Volume Deformation Model and Its Applications in Facial Motion Capture (H Tao & T S Huang); Nonrigid Motion and Structure Analysis from 2D with Application Towards 3D Cloud Tracking (L Zhou et al.); Map Structure Recognition and Automatic Map Data Acquisition (Y Liu); Learning Visual Concepts for Content Based Retrieval (M S Lew); Automated Human Facial Feature Extraction Using Double Resolution Pyramid (L Tang); Learning Based Relevance Feedback in Image Retrieval (Y Rui & T Huang); Object-Based Subband/Wavelet Video Compression (S-C Han & J W Woods); A Computational Approach to Semantic Event Detection in Video (R J Qian et al.); Robust Video Transmission for Feedback Channels (S D Blostein & Q Jiang); Multidimensional AM-FM Models with Image Processing Applications (M S Pattichis et al.); Image Transmission Over Noisy Channels: TCQ-Based Coding Schemes (C W Chen et al.). Readership: Graduates, academics and researchers in image processing, artificial intelligence, machine perception and neural networks.
Local Note:
Electronic reproduction. Ann Arbor, Michigan : ProQuest Ebook Central, 2017. Available via World Wide Web. Access may be limited to ProQuest Ebook Central affiliated libraries.
Genre:
Electronic Access:
Click to View