| Preface | p. XIII |
| Featured Chapters | p. 1 |
| IMET: Image Mining for Typhoon Analysis | p. 7 |
| Introduction | p. 7 |
| Typhoon from an Informatics Perspective | p. 8 |
| Meteorological Background | p. 8 |
| Challenges to Informatics | p. 8 |
| Typhoon Image Collection | p. 10 |
| Typhoon Images from a CBIR Perspective | p. 11 |
| Scientific Application and Narrow Domain | p. 11 |
| Time-Series Data in Sequences | p. 11 |
| Variability of Cloud Patterns | p. 11 |
| Characteristic Scale | p. 12 |
| Invariance | p. 12 |
| Multi-spectral Images | p. 12 |
| Metadata and Annotation | p. 13 |
| Representation of the Typhoon | p. 13 |
| Component-based Representation | p. 13 |
| Multi-scale Representation | p. 15 |
| Shape-based Representation | p. 15 |
| Image Mining | p. 15 |
| Finding Typical Patterns | p. 15 |
| Image Mining and CBIR | p. 17 |
| Image Mining Environment for Typhoon Analysis and Prediction | p. 18 |
| System Architecture | p. 18 |
| Query Language | p. 19 |
| Exploration with IMET | p. 21 |
| Search by Metadata | p. 21 |
| Spatial Data Mining | p. 21 |
| Comparison of Multiple Typhoon Sequences | p. 22 |
| Temporal Data Mining | p. 22 |
| Conclusion | p. 23 |
| Acknowledgment | p. 24 |
| References | p. 24 |
| Discovering Patterns with and within Images | p. 27 |
| Introduction | p. 27 |
| What is Image Mining? | p. 27 |
| Image Mining versus Content-based Image Retrieval | p. 28 |
| Issues and Challenges | p. 30 |
| Image Mining Techniques | p. 32 |
| Content-based and non-content-based image mining | p. 32 |
| Image Mining Techniques | p. 33 |
| Classification of images and/or image content | p. 33 |
| Image clustering | p. 34 |
| Association Rule Mining within images | p. 35 |
| Pre-processing images presents a challenge | p. 37 |
| Conclusion | p. 39 |
| References | p. 40 |
| A System Supporting Semantics Retrieval | p. 43 |
| Introduction | p. 43 |
| Scenery Analyzer: System Framework | p. 45 |
| A Hierarchical Representation for Low-Level Features | p. 47 |
| Extracting Semantic Features | p. 50 |
| Classifying Textons | p. 51 |
| Clustering Textons | p. 53 |
| Rendering Semantic Regions | p. 53 |
| Case Study of Semantic Features | p. 54 |
| Background and Sky | p. 54 |
| Ground | p. 54 |
| Wave | p. 55 |
| Green Tree | p. 55 |
| Building | p. 55 |
| Conclusion | p. 57 |
| References | p. 58 |
| Techniques for Color-Based Image Retrieval | p. 61 |
| Introduction | p. 61 |
| Color-Spaces | p. 63 |
| Color-based image description | p. 64 |
| Static reduction methods | p. 65 |
| Dynamic reduction methods | p. 65 |
| Visual features extraction and representation | p. 67 |
| Global representations | p. 67 |
| Partition-based representations | p. 68 |
| Regional representations | p. 68 |
| Distance Function | p. 69 |
| Similarity Search | p. 70 |
| Filtering | p. 71 |
| Spatial access methods - SAMs | p. 72 |
| Metric access methods - MAMs | p. 72 |
| Approximate and non-metric methods | p. 72 |
| Existing CBIR approaches | p. 73 |
| Global approaches | p. 73 |
| Partition-based approaches | p. 75 |
| Regional approaches | p. 76 |
| Open problems | p. 78 |
| Summary | p. 79 |
| Acknowledgment | p. 79 |
| References | p. 80 |
| Recovering in Video Documents | p. 83 |
| Introduction | p. 83 |
| Temporal video segmentation | p. 85 |
| Computation of optical flow | p. 86 |
| Orthogonal Dynamic Programming | p. 87 |
| Building and selection of trajectories | p. 88 |
| Turning sequences of vector fields into sets of trajectories | p. 90 |
| Building trajectories for a reference frame | p. 90 |
| Building trajectories using several reference frames | p. 91 |
| Selecting reliable and optimally spread trajectories | p. 92 |
| Use of the gradient of the image intensity | p. 92 |
| Module of the gradient of vector field | p. 93 |
| Shi-Tomasi-Kanade eigenvalues | p. 93 |
| Conservation of a transported window | p. 94 |
| Selection of trajectories | p. 95 |
| Camera model | p. 95 |
| Pinhole camera model | p. 95 |
| Intrinsic parameters | p. 96 |
| Extrinsic parameters | p. 96 |
| Video sequence camera parameters | p. 97 |
| Recovery of camera motion without parallax | p. 99 |
| Search for homographies and background regions | p. 99 |
| Search for camera parameters | p. 102 |
| Search for local parameters | p. 103 |
| Search for global parameters | p. 104 |
| Search for all parameters | p. 105 |
| Sample results | p. 105 |
| Recovery of camera motion with parallax | p. 107 |
| Integration | p. 109 |
| Conclusion | p. 110 |
| Acknowledgments | p. 110 |
| References | p. 110 |
| Mining of Video Database | p. 113 |
| Introduction | p. 113 |
| Semantics-Sensitive Video Database Model | p. 115 |
| Video Analysis and Feature Extraction | p. 119 |
| Semantics-Sensitive Video Classification | p. 121 |
| Hierarchical Database Indexing and Access | p. 129 |
| Conclusions | p. 135 |
| Acknowledgement | p. 136 |
| References | p. 136 |
| Medical Multimedia Databases | p. 139 |
| Introduction | p. 139 |
| Review of Medical Multimodality and Multimedia Systems | p. 140 |
| Content-based medical image retrieval techniques | p. 141 |
| Brain image segmentation techniques | p. 142 |
| Intensity-based segmentation methods | p. 142 |
| Texture-based segmentation methods | p. 143 |
| Model-based segmentation methods | p. 144 |
| Segmentation and measurements in MR images | p. 144 |
| Multimedia and multimodality based medical systems | p. 146 |
| The MEDIMAGE System | p. 147 |
| The MEDIMAGE system databases | p. 148 |
| The MEDIMAGE MR image processing tools | p. 149 |
| The MEDIMAGE database management tools | p. 149 |
| Results obtained with the MEDIMAGE system | p. 150 |
| The MEDIMAGE system summary | p. 153 |
| The Epilepsy System | p. 153 |
| The Epilepsy system architecture | p. 153 |
| The Epilepsy system methods | p. 155 |
| Results obtaining with the Epilepsy system | p. 155 |
| Conclusions | p. 157 |
| References | p. 158 |
| An Object Approach for Web Presentations | p. 161 |
| Introduction | p. 161 |
| The V-STORM System | p. 162 |
| The AROM System | p. 164 |
| Coupling AROM and V-STORM | p. 165 |
| An AROM Model for Multimedia Presentations | p. 165 |
| Building a multimedia presentation | p. 168 |
| Benefits of the AVS model | p. 169 |
| The Template model | p. 170 |
| Template definition | p. 170 |
| Spatial Description | p. 171 |
| Temporal Description | p. 172 |
| Translation into AROM | p. 173 |
| From Templates to SMIL Presentations | p. 173 |
| Related Works | p. 175 |
| Conclusion | p. 176 |
| References | p. 177 |
| Web Multiform Data Structuring | p. 179 |
| Introduction | p. 179 |
| Related work | p. 181 |
| Data integration | p. 181 |
| XML Mapping | p. 182 |
| XML query languages | p. 182 |
| UML conceptual model | p. 183 |
| XML logical model | p. 185 |
| XML physical model | p. 187 |
| Transformation algorithm | p. 187 |
| Implementation | p. 188 |
| Architecture | p. 188 |
| Attribute extraction | p. 189 |
| XML document generation | p. 190 |
| Output | p. 190 |
| Mapping into a relational database | p. 193 |
| Conclusion and future issues | p. 193 |
| References | p. 194 |
| Media Annotation | p. 197 |
| Introduction | p. 197 |
| Generation of describers | p. 197 |
| Segmentation and text annotation | p. 197 |
| Images and annotations | p. 200 |
| Audio segmentation and annotation | p. 201 |
| Segmentation and annotation of animated image | p. 202 |
| Dimensions | p. 204 |
| Querying | p. 205 |
| Conclusion | p. 208 |
| References | p. 208 |
| Audio Content-based Classification | p. 213 |
| Introduction | p. 213 |
| Framework of semantic classes | p. 215 |
| Silence Description | p. 216 |
| Speech Description | p. 217 |
| Music Description | p. 217 |
| Noise Description | p. 218 |
| Classification method | p. 218 |
| Retrieval | p. 221 |
| Experimentation | p. 222 |
| Format of Sound data storage | p. 222 |
| Evaluation method | p. 222 |
| Data sets | p. 223 |
| Sample of an audio material | p. 223 |
| Results and analysis | p. 224 |
| Comparison with related works | p. 225 |
| Conclusion | p. 226 |
| Acknowledgment | p. 227 |
| References | p. 227 |
| Index | p. 229 |
| Table of Contents provided by Ingram. All Rights Reserved. |
