SpringerLink Springer Engineering eBooks 2017 English+International

Incluye referencias bibliográficas e índice

Preface; Contents; Contributors; Acronyms; 1 Feature Representation and Extraction for Image Search and Video Retrieval; 1.1 Introduction; 1.2 Spatial Pyramid Matching, Soft Assignment Coding, Fisher Vector Coding, and Sparse Coding; 1.2.1 Spatial Pyramid Matching; 1.2.2 Soft Assignment Coding; 1.2.3 Fisher Vector Coding; 1.2.4 Sparse Coding; 1.2.5 Some Sparse Coding Variants; 1.3 Local Binary Patterns (LBP), Feature LBP (FLBP), Local Quaternary Patterns (LQP), and Feature LQP (FLQP); 1.4 Scale Invariant Feature Transform (SIFT) and SIFT Variants; 1.4.1 Color SIFT; 1.4.2 SURF; 1.4.3 MSIFT.

1.4.4 DSP-SIFT1.4.5 LPSIFT; 1.4.6 FAIR-SURF; 1.4.7 Laplacian SIFT; 1.4.8 Edge-SIFT; 1.4.9 CSIFT; 1.4.10 RootSIFT; 1.4.11 PCA-SIFT; 1.5 Conclusion; References; 2 Learning and Recognition Methods for Image Search and Video Retrieval; 2.1 Introduction; 2.2 Deep Learning Networks and Models; 2.2.1 Feedforward Deep Neural Networks; 2.2.2 Deep Autoencoders; 2.2.3 Convolutional Neural Networks (CNNs); 2.2.4 Deep Boltzmann Machine (DBM); 2.3 Support Vector Machines; 2.3.1 Linear Support Vector Machine; 2.3.2 Soft-Margin Support Vector Machine; 2.3.3 Non-linear Support Vector Machine.

2.3.4 Simplified Support Vector Machines2.3.5 Efficient Support Vector Machine; 2.3.6 Applications of SVM; 2.4 Other Popular Kernel Methods and Similarity Measures; 2.5 Conclusion; References; 3 Improved Soft Assignment Coding for Image Classification; 3.1 Introduction; 3.2 Related Work; 3.3 The Improved Soft-Assignment Coding; 3.3.1 Revisiting the Soft-Assignment Coding; 3.3.2 Introduction to Fisher Vector and VLAD Method; 3.3.3 The Thresholding Normalized Visual Word Plausibility; 3.3.4 The Power Transformation; 3.3.5 Relation to VLAD Method; 3.4 Experiments.

3.4.1 The UIUC Sports Event Dataset3.4.2 The Scene 15 Dataset; 3.4.3 The Caltech 101 Dataset; 3.4.4 The Caltech 256 Dataset; 3.4.5 In-depth Analysis; 3.5 Conclusion; References; 4 Inheritable Color Space (InCS) and Generalized InCS Framework with Applications to Kinship Verification; 4.1 Introduction; 4.2 Related Work; 4.3 A Novel Inheritable Color Space (InCS); 4.4 Properties of the InCS; 4.4.1 The Decorrelation Property; 4.4.2 Robustness to Illumination Variations; 4.5 The Generalized InCS (GInCS) Framework; 4.6 Experiments.

4.6.1 Experimental Results Using the KinFaceW-I and the KinFaceW-II Datasets4.6.2 Experimental Results Using the UB KinFace Dataset; 4.6.3 Experimental Results Using the Cornell KinFace Dataset; 4.7 Comprehensive Analysis; 4.7.1 Comparative Evaluation of the InCS and Other Color Spaces; 4.7.2 The Decorrelation Property of the InCS Method; 4.7.3 The Robustness of the InCS and the GInCS to Illumination Variations; 4.7.4 Performance of Different Color Components of the InCS and the GInCS; 4.7.5 Comparison Between the InCS and the Generalized InCS.

This book initially reviews the major feature representation and extraction methods and effective learning and recognition approaches, which have broad applications in the context of intelligent image search and video retrieval. It subsequently presents novel methods, such as improved soft assignment coding, Inheritable Color Space (InCS) and the Generalized InCS framework, the sparse kernel manifold learner method, the efficient Support Vector Machine (eSVM), and the Scale-Invariant Feature Transform (SIFT) features in multiple color spaces. Lastly, the book presents clothing analysis for subject identification and retrieval, and performance evaluation methods of video analytics for traffic monitoring. Digital images and videos are proliferating at an amazing speed in the fields of science, engineering and technology, media and entertainment. With the huge accumulation of such data, keyword searches and manual annotation schemes may no longer be able to meet the practical demand for retrieving relevant content from images and videos, a challenge this book addresses.