»ùÓÚÓïÒåµÄͼÏñ¼ìË÷

PrefaceList of AbbreviationsChapter 1 Introduction1£®1 Background1£®1£®1 The 'Semantic Gap1£®1£®2 Query by Keywords1£®2 Objectives1£®3 Contributions of this Book1£®3£®1 Identifying Existing Semantic Learning Techniques1£®3£®2 Designing Effective Feature Extraction Methods for Arbitrary-Shaped Regions\"1£®3£®3 High-Level Concept Learning Using Decision Tree1£®3£®4 Applying RBIR with Semantics to Web Image Search1£®4 Organization of the BookChapter 2 Key Techniques in Semantic-Based Image Retrieval2£®1 Introduction2£®2 Techniques and Issues in Region-Based Image Retrieval2£®2£®1 Image Segmentation2£®2£®2 Low-Level Image Feature Extraction2£®2£®3 Similarity Measure2£®2£®4 Test Database and Performance Evaluation2£®3 High-Level Image Semantic Learning Techniques2£®3£®1 Object-Ontology2£®3£®2 Machine Learning2£®3£®3 Relevance Feedback (RF)2£®3£®4 Semantic Template2£®3£®5 Fusion of Multiple Resources for Web Image Search2£®3£®6 Deep Learning2£®3£®7 Summary of Existing Techniques in Image Semantic Learning2£®4 Research Problems Addressed in this BookChapter 3 Deriving Image Semantics from Color Features3£®1 Introduction3£®2 Region Color Feature Extraction and Semantic Color Naming3£®2£®1 Region Color Features3£®2£®2 Semantic Color Names3£®3 Image Retrieval using Semantic Color Names3£®3£®1 RBIR with Semantic Color Names3£®3£®2 Feature Normalization3£®3£®3 Image Similarity Measure using EMD3£®4 Results and Analysis3£®4£®1 Test Database and Performance Evaluation Model3£®4£®2 Comparison of Different Color Features3£®4£®3 Performance of the Proposed Color Naming Method3£®4£®4 Image Retrieval with Color Names£¬ Region Color Features and GlobalColor Features3£®5 Discussion and ConclusionsChapter 4 Effective Texture Feature Extraction from Arbitrary-Shaped Regions4£®1 Introduction4£®2 Deriving Texture Features from Arbitrary-Shaped Regions4£®2£®1 Projection onto Convex Set (POCS) Theory4£®2£®2 Extracting Region Texture Features Using POCS-ER4£®2£®3 Theoretical Analysis of POCS-ER4£®2£®4 Implementation of POCS-ER4£®3 POCS-ER on Brodatz Textures4£®3£®1 Illustration of POCS-ER Process4£®3£®2 Performance of POCS-ER Measured by PSNR4£®3£®3 Performance of POCS-ER Measured by Retrieval Performance4£®4 POCS-ER for Real-World Image Retrieval4£®4£®1 Experimental Setups4£®4£®2 Performance of Different Texture Feature Extraction Methods in RBIR£®£®£®4£®4£®3 RBIR with Color£¬ Texture£¬ Color & Texture4£®4£®4 Comparison of Region Features and Global Features in Image Retrieval4£®5 Conclusions and DiscussionChapter 5 Deriving High-Level Image Concepts Using Decision Tree Learning5£®1 Introduction5£®2 Decision Tree Learning5£®2£®1 Overview5£®2£®2 Decision Tree Induction for Image Semantic Learning5£®3 The Proposed Decision Tree Induction Algorithm DT-ST5£®3£®1 Semantic Template Construction5£®3£®2 Image Feature Discretization5£®3£®3 Decision Tree Induction5£®4 Results and Analysis5£®4£®1 Selection of Pre-pnming Threshold5£®4£®2 Pruning Unknowns5£®4£®3 Handling Queries with Concepts outside the Training Concept Set5£®4£®4 Comparison of DT-ST with ID3 and C4£®55£®5 Region-Based Image Retrieval with High-Level Semantics5£®6 Discussion5£®6£®1 Scalability of DT-ST5£®6£®2 The Advantage of Image Retrieval with High-Level Concepts5£®7 ConclusionsChapter 6 Application of Semantic-Based RBIR to Web Image Search6£®1 Introduction6£®2 The False Filtering Algorithm6£®3 Results and Analysis6£®3£®1 Web Image Collection and Performance Evaluation6£®3£®2 Experimental Results6£®4 Discussions6£®4£®1 Integration6£®4£®2 FF Response Time6£®4£®3 Scalability6£®5 ConclusionsChapter 7 Conclusions and Future Work7£®1 Conclusions of this Book7£®2 Future Research DirectionsBibliographyAppendix A HSV Color Histogram and HSV-RGB ConversionAppendix B Tamura Texture FeaturesAppendix C lllustration of POCS-ER Process Using ZR and MPAppendix D Pre-pruning &Post-pruning in DT-ST