Exploration of visual data /
Xiang Sean Zhou, Yong Rui, Thomas S. Huang.
- Boston : Kluwer Academic Publishers, 2003.
- xvi, 187 p. : ill. ; 24 cm.
- The Kluwer international series in video computing .
Includes bibliographical references (p. [167]-183) and index.
Introduction. 1.1. Challenges. 1.2. Research Scope. 1.3. State-of-the-Art. 1.4. Outline of Book. 2: Overview Of Visual Information Representation. 2.1. Color. 2.2. Texture. 2.3. Shape. 2.4. Spatial Layout. 2.5. Interest Points. 2.6. Image Segmentation. 2.7. Summary. 3: Edge- based Structural Features. 3.1. Visual Feature Representation. 3.2. Edge-Based Structural Features. 3.3. Experiments and Analysis. 4: Probabilistic Local Structure Models. 4.1. Introduction. 4.2. The Proposed Modeling Scheme. 4.3. Implementation Issues. 4.4. Experiments and Discussion. 4.5. Summary and Discussion. 5: Constructing Table-of-Content for Videos. 5.1. Introduction. 5.2. Related Work. 5.3. The Proposed Approach. 5.4. Determination of the Parameters. 5.5. Experimental Results. 5.6. Conclusions. 6: Nonlinearly Sampled Video Streaming. 6.1. Introduction. 6.2. Problem Statement. 6.3. Frame Saliency Scoring. 6.4. Scenario and Assumptions. 6.5. Minimum Buffer Formulation. 6.6. Limited-Buffer Formulation. 6.7. Extensions and Analysis. 6.8. Experimental Evaluation. 6.9. Discussion. 7: Relevance Feedback for Visual Data Retrieval. 7.1. The Need for User-in-the-Loop. 7.2. Problem Statement. 7.3. Overview of Existing Techniques. 7.4.Learning from Positive Feedbacks. 7.5. Adding Negative Feedbacks: Discriminant Analysis? 7.6. Biased Discriminant Analysis. 7.7. Nonlinear Extensions Using Kernel and Boosting. 7.8. Comparisons and Analysis. 7.9. Relevance Feedback on Image Tiles. 8: Toward Unification of Keywords and Low- Level Contents. 8.1. Introduction. 8.2. Joint Querying and Relevance Feedback. 8.3. Learning Semantic Relations between Keywords. 8.4. Discussion. 9: Future Research Directions. 9.1. Low-level and intermediate-level visual descriptors. 9.2. Learning from user interactions. 9.3. Unsupervised detection of patterns/events. 9.4. Domain- specific applications. References. Index.
Presents research efforts in the area of content-based exploration of image and video data. The two key issues emphasized are "content-awareness" and "user-in-the-loop". This work provides a comprehensive review on algorithms for visual feature extraction based on color, texture, shape, and structure.