Benutzerdefiniertes Cover
Visual Indexing and Retrieval / by Jenny Benois-Pineau, Frédéric Precioso, Matthieu Cord
Mitwirkende(r): Resource type: Ressourcentyp: Buch (Online)Buch (Online)Sprache: Englisch Reihen: SpringerBriefs in Computer Science | SpringerLink BücherVerlag: New York, NY : Springer New York, 2012Beschreibung: Online-Ressource (VIII, 107p. 17 illus, digital)ISBN:- 9781461435884
- 9781461435877
- 1280793252
- 9781280793257
- 006.7
- 005.74
- QA76.575
Inhalte:
Zusammenfassung: Matthieu CordZusammenfassung: The research in content-based indexing and retrieval of visual information such as images and video has become one of the most populated directions in the vast area of information technologies. Social networks such as YouTube, Facebook, FileMobile, and DailyMotion host and supply facilities for accessing a tremendous amount of professional and user generated data. The areas of societal activity, such as, video protection and security, also generate thousands and thousands of terabytes of visual content. This book presents the most recent results and important trends in visual information indexing and retrieval. It is intended for young researchers, as well as, professionals looking for an algorithmic solution to a problem.PPN: PPN: 1651472785Package identifier: Produktsigel: ZDB-2-SCS
Visual Indexing and Retrieval; Preface; Contents; Chapter 1 Introduction; 1.1 Context and motivations; 1.2 Outline of the book; Chapter 2 Visual feature extraction and description; 2.1 Introduction; 2.2 Visual primitive detection; 2.2.1 Point-based detectors; 2.2.2 Region-based detectors; 2.2.3 Spatio-temporal extension; 2.3 Descriptors; 2.3.1 Feature spaces used by descriptors; 2.3.1.1 Color; 2.3.1.2 Texture; 2.3.1.3 Shape; 2.3.1.4 Edge; 2.3.2 Scale Invariant Feature Transform; 2.3.3 Speeded Up Robust Features; 2.3.4 Global GIST descriptor; 2.4 Evaluation of feature detectors and descriptors
2.5 ConclusionChapter 3 Machine learning approaches for visual information retrieval; 3.1 Bag-of-Feature representations and similarities; 3.1.1 Bag-of-Visual-Words approaches (BoVW); 3.1.2 Vector distances and kernel functions; 3.1.3 Bag-of-Features (BoF) similarity and retrieval; 3.1.3.1 Voting-based Strategy; 3.1.3.2 Kernel on Bag-of-Features; 3.2 Learning algorithms; 3.2.1 Support Vector Machines; Optimization formulation; Solvers; 3.2.2 Multiple Kernel Learning for feature combination; 3.2.3 Boosting; 3.2.4 Linear Programming Boosting (LPBoost) for Multiple Kernel Learning (MKL)
3.2.5 Interactive learning3.3 Conclusion; Chapter 4 Spatial and multi-resolution context in visual indexing; 4.1 Introduction; 4.2 Incorporating spatial context; 4.2.1 Local histograms of visual words; 4.2.2 Context-matching kernels; 4.2.3 Graph-matching; 4.2.4 Graph Words; Graph feature construction; The nested layered approach; Graph comparison; Visual dictionaries and signatures; Experiments; Evaluation protocol; The multilayer approach; 4.3 Multi-resolution in visual indexing; 4.3.1 Low resolution and Rough Indexing Paradigm; 4.3.2 Multi-resolution and multiscale in image indexing.
4.3.3 Multi-resolution features and visual dictionariesMulti-resolution approach on wavelet pyramids; Merging the information at different resolutions; 4.4 Conclusion; Chapter 5 Scalability issues in visual information retrieval; 5.1 Introduction; 5.2 Scalable Retrieval and Mining: A Typology of Problems; 5.3 Principled Approaches to Scalability; 5.3.1 Scalable Retrieval; 5.3.2 Scalable Mining; 5.3.3 How to Evaluate Scalability; 5.4 Trends in Scalable Visual Information Retrieval; 5.4.1 Complex Data; 5.4.2 Optimized Representations and Scalability; 5.4.3 Distributed Data and Resources
5.5 ConclusionChapter 6 Evaluation of visual information indexing and retrieval; 6.1 Introduction; 6.2 Organizing an evaluation campaign; 6.2.1 Organization; 6.2.2 Terminology; 6.2.3 Agenda; 6.2.4 Copyrights and legal matters on the content set distribution and exploitation; 6.2.5 Ground truth and annotation process; 6.2.6 Evaluation metrics; 6.3 Main evaluation campaigns overview; 6.3.1 TRECVID; 6.3.2 PASCAL VOC and ILSVRC; 6.3.3 Other evaluation campaigns; 6.4 Conclusion; References;
Dieser Titel hat keine Exemplare