| Description |
1 online resource (1 volume) : illustrations |
| Bibliography |
Includes bibliographical references. |
| Contents |
Front Cover; Learning-Based Local Visual Representation and Indexing; Copyright; Contents; Preface; List of Figures; List of Tables; List of Algorithms; Chapter 1: Introduction; 1.1 Background and Significance; 1.2 Literature Review of the Visual Dictionary; 1.2.1 Local Interest-Point Extraction; 1.2.2 Visual-Dictionary Generation and Indexing ; 1.3 Contents of This Book; Chapter 2: Interest-Point Detection: Beyond Local Scale; 2.1 Introduction; 2.2 Difference of Contextual Gaussians; 2.2.1 Local Interest-Point Detection; 2.2.2 Accumulating Contextual Gaussian Difference. |
|
2.3 Mean Shift-Based Localization2.3.1 Localization Algorithm ; 2.3.2 Comparison to Saliency; 2.4 Detector Learning; 2.5 Experiments; 2.5.1 Database and Evaluation Criteria; 2.5.2 Detector Repeatability; 2.5.3 CASL for Image Search and Classification; 2.6 Summary; Chapter 3: Unsupervised Dictionary Optimization; 3.1 Introduction; 3.2 Density-Based Metric Learning; 3.2.1 Feature-Space Density-Field Estimation ; 3.2.2 Learning a Metric for Quantization; 3.3 Chain-Structure Recognition ; 3.3.1 Chain Recognition in Dictionary Hierarchy; 3.4 Dictionary Transfer Learning. |
|
3.4.1 Cross-database Case3.4.2 Incremental Transfer; 3.5 Experiments; 3.5.1 Quantitative results; 3.6 Summary; Chapter 4: Supervised Dictionary Learning via Semantic Embedding ; 4.1 Introduction; 4.2 Semantic Labeling Propagation; 4.2.1 Density Diversity Estimation ; 4.3 Supervised Dictionary Learning; 4.3.1 Generative Modeling ; 4.3.2 Supervised Quantization ; 4.4 Experiments; 4.4.1 Database and Evaluations; 4.4.2 Quantitative Results; 4.5 Summary; Chapter 5: Visual Pattern Mining; 5.1 Introduction; 5.2 Discriminative 3D Pattern Mining; 5.2.1 The Proposed Mining Scheme. |
|
5.2.2 Sparse Pattern Coding5.3 CBoP for Low Bit Rate Mobile Visual Search; 5.4 Quantitative Results; 5.4.1 Data Collection; 5.4.2 Evaluation Criteria; 5.4.3 Baselines; 5.4.4 Quantitative Performance; 5.5 Conclusion; Conclusions; References. |
| Summary |
Learning-Based Local Visual Representation and Indexing , reviews the state-of-the-art in visual content representation and indexing, introduces cutting-edge techniques in learning based visual representation, and discusses emerging topics in visual local representation, and introduces the most recent advances in content-based visual search techniques. Discusses state-of-the-art procedures in learning-based local visual representation. Shows how to master the basic techniques needed for building a large-scale visual search engine and indexing system Provides insight into how machine learning techniques can be leveraged to refine the visual recognition system, especially in the part of visual feature representation. |
| Subject |
Computer vision.
|
|
Pattern recognition systems.
|
|
Pattern Recognition, Automated |
|
Vision par ordinateur. |
|
Reconnaissance des formes (Informatique) |
|
Computer vision |
|
Pattern recognition systems |
|
Visualisierung |
|
Bilddatenbank |
|
Bildverstehen |
|
Visuelle Suche |
|
Mustererkennung |
|
Maschinelles Lernen |
| Added Author |
Rongrong, Ji, author.
|
|
Yao, Hongxun, author.
|
|
Gao, Yue, author.
|
|
Duan, Ling-Yu, author.
|
|
Dai, Qionghai, author.
|
| Other Form: |
Print version: Learning-based local visual representation and indexing 9780128026205 (OCoLC)894611891 |
| ISBN |
9780128026205 |
|
0128026200 |
|
0128024097 |
|
9780128024096 |
|
More Resources