Muutke küpsiste eelistusi

Computer Vision Using Local Binary Patterns 2011 [Kõva köide]

  • Formaat: Hardback, 212 pages, kõrgus x laius: 235x155 mm, kaal: 512 g, XVI, 212 p., 1 Hardback
  • Sari: Computational Imaging and Vision 40
  • Ilmumisaeg: 22-Jun-2011
  • Kirjastus: Springer London Ltd
  • ISBN-10: 0857297473
  • ISBN-13: 9780857297471
  • Kõva köide
  • Hind: 48,70 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Tavahind: 57,29 €
  • Säästad 15%
  • Raamatu kohalejõudmiseks kirjastusest kulub orienteeruvalt 2-4 nädalat
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Tellimisaeg 2-4 nädalat
  • Lisa soovinimekirja
  • Formaat: Hardback, 212 pages, kõrgus x laius: 235x155 mm, kaal: 512 g, XVI, 212 p., 1 Hardback
  • Sari: Computational Imaging and Vision 40
  • Ilmumisaeg: 22-Jun-2011
  • Kirjastus: Springer London Ltd
  • ISBN-10: 0857297473
  • ISBN-13: 9780857297471
The recent emergence of Local Binary Patterns (LBP) has led to significant progress in applying texture methods to various computer vision problems and applications. The focus of this research has broadened from 2D textures to 3D textures and spatiotemporal (dynamic) textures. Also, where texture was once utilized for applications such as remote sensing, industrial inspection and biomedical image analysis, the introduction of LBP-based approaches have provided outstanding results in problems relating to face and activity analysis, with future scope for face and facial expression recognition, biometrics, visual surveillance and video analysis.Computer Vision Using Local Binary Patterns provides a detailed description of the LBP methods and their variants both in spatial and spatiotemporal domains. This comprehensive reference also provides an excellent overview as to how texture methods can be utilized for solving different kinds of computer vision and image analysis problems. Source codes of the basic LBP algorithms, demonstrations, some databases and a comprehensive LBP bibliography can be found from an accompanying web site.Topics include: local binary patterns and their variants in spatial and spatiotemporal domains, texture classification and segmentation, description of interest regions, applications in image retrieval and 3D recognition - Recognition and segmentation of dynamic textures, background subtraction, recognition of actions, face analysis using still images and image sequences, visual speech recognition and LBP in various applications.Written by pioneers of LBP, this book is an essential resource for researchers, professional engineers and graduate students in computer vision, image analysis and pattern recognition. The book will also be of interest to all those who work with specific applications of machine vision.

Written by the pioneers of local binary patterns, and including a wealth of illustrations, this book gives those working with LBPs a single-source, comprehensive resource on the uses of LBP methodology, in both spatial and spatiotemporal domains.

Arvustused

From the reviews:

This book will be of interest mainly to computer vision practitioners and other researchers interested in visual pattern recognition techniques. It presents local binary patterns and their many variants and applications. this monograph is an accessible introduction to and survey of the local pattern approach to visual recognition by the group that has the most extensive experience with it. the book will be a valuable addition to the library of any specialist working in these areas. (Bill Triggs, SIAM Review, Vol. 54 (4), 2012)

Part I Local Binary Pattern Operators
1 Background
3(10)
1.1 The Role of Texture in Computer Vision
3(1)
1.2 Motivation and Background for LBP
4(2)
1.3 A Brief History of LBP
6(1)
1.4 Overview of the Book
7(6)
References
10(3)
2 Local Binary Patterns for Still Images
13(36)
2.1 Basic LBP
13(1)
2.2 Derivation of the Generic LBP Operator
13(3)
2.3 Mappings of the LBP Labels: Uniform Patterns
16(2)
2.4 Rotational Invariance
18(3)
2.4.1 Rotation Invariant LBP
19(1)
2.4.2 Rotation Invariance Using Histogram Transformations
20(1)
2.5 Complementary Contrast Measure
21(2)
2.6 Non-parametric Classification Principle
23(1)
2.7 Multiscale LBP
24(1)
2.8 Center-Symmetric LBP
25(1)
2.9 Other LBP Variants
26(23)
2.9.1 Preprocessing
26(5)
2.9.2 Neighborhood Topology
31(1)
2.9.3 Thresholding and Encoding
32(3)
2.9.4 Multiscale Analysis
35(2)
2.9.5 Handling Rotation
37(1)
2.9.6 Handling Color
38(1)
2.9.7 Feature Selection and Learning
39(3)
2.9.8 Complementary Descriptors
42(1)
2.9.9 Other Methods Inspired by LBP
42(1)
References
43(6)
3 Spatiotemporal LBP
49(20)
3.1 Basic VLBP
49(3)
3.2 Rotation Invariant VLBP
52(1)
3.3 Local Binary Patterns from Three Orthogonal Planes
53(4)
3.4 Rotation Invariant LBP-TOP
57(4)
3.4.1 Problem Description
57(2)
3.4.2 One Dimensional Histogram Fourier LBP-TOP (1DHFLBP-TOP)
59(2)
3.5 Other Variants of Spatiotemporal LBP
61(8)
References
64(5)
Part II Analysis of Still Images
4 Texture Classification and Segmentation
69(12)
4.1 Texture Classification
69(4)
4.1.1 Texture Image Datasets
70(2)
4.1.2 Texture Classification Experiments
72(1)
4.2 Unsupervised Texture Segmentation
73(4)
4.2.1 Overview of the Segmentation Algorithm
74(1)
4.2.2 Splitting
75(1)
4.2.3 Agglomerative Merging
75(1)
4.2.4 Pixelwise Classification
76(1)
4.2.5 Experiments
77(1)
4.3 Discussion
77(4)
References
78(3)
5 Description of Interest Regions
81(8)
5.1 Related Work
81(1)
5.2 CS-LBP Descriptor
82(2)
5.3 Image Matching Experiments
84(3)
5.3.1 Matching Results
86(1)
5.4 Discussion
87(2)
References
88(1)
6 Applications in Image Retrieval and 3D Recognition
89(20)
6.1 Block-Based Methods for Image Retrieval
89(7)
6.1.1 Description of the Method
90(2)
6.1.2 Experiments
92(3)
6.1.3 Discussion
95(1)
6.2 Recognition of 3D Textured Surfaces
96(13)
6.2.1 Texture Description by LBP Histograms
97(1)
6.2.2 Use of Multiple Histograms as Texture Models
98(1)
6.2.3 Experiments with CUReT Textures
99(2)
6.2.4 Experiments with Scene Images
101(1)
6.2.5 Discussion
102(2)
References
104(5)
Part III Motion Analysis
7 Recognition and Segmentation of Dynamic Textures
109(18)
7.1 Dynamic Texture Recognition
109(7)
7.1.1 Related Work
109(1)
7.1.2 Measures
110(1)
7.1.3 Multi-resolution Analysis
111(1)
7.1.4 Experimental Setup
111(1)
7.1.5 Results for VLBP
112(1)
7.1.6 Results for LBP-TOP
113(2)
7.1.7 Experiments of Rotation Invariant LBP-TOP to View Variations
115(1)
7.2 Dynamic Texture Segmentation
116(7)
7.2.1 Related Work
116(2)
7.2.2 Features for Segmentation
118(2)
7.2.3 Segmentation Procedure
120(2)
7.2.4 Experiments
122(1)
7.3 Discussion
123(4)
References
124(3)
8 Background Subtraction
127(8)
8.1 Related Work
127(1)
8.2 An LBP-based Approach
128(2)
8.2 Modifications of the LBP Operator
128(1)
8.2.2 Background Modeling
129(1)
8.2.3 Foreground Detection
130(1)
8.3 Experiments
130(3)
8.4 Discussion
133(2)
References
134(1)
9 Recognition of Actions
135(16)
9.1 Related Work
135(1)
9.2 Static Texture Based Description of Movements
136(2)
9.3 Dynamic Texture Method for Motion Description
138(4)
9.3.1 Human Detection with Background Subtraction
138(1)
9.3.2 Action Description
139(2)
9.3.3 Modeling Temporal Information with Hidden Markov Models
141(1)
9.4 Experiments
142(3)
9.5 Discussion
145(6)
References
146(5)
Part IV Face Analysis
10 Face Analysis Using Still Images
151(18)
10.1 Face Description Using LBP
151(2)
10.2 Eye Detection
153(1)
10.3 Face Detection
154(5)
10.4 Face Recognition
159(5)
10.5 Facial Expression Recognition
164(1)
10.6 LBP in Other Face Related Tasks
165(1)
10.7 Conclusion
165(4)
References
165(4)
11 Face Analysis Using Image Sequences
169(12)
11.1 Facial Expression Recognition Using Spatiotemporal LBP
169(4)
11.2 Face Recognition from Videos
173(3)
11.3 Gender Classification from Videos
176(2)
11.4 Discussion
178(3)
References
179(2)
12 Visual Recognition of Spoken Phrases
181(12)
12.1 Related Work
181(1)
12.2 System Overview
182(1)
12.3 Local Spatiotemporal Descriptors for Visual Information
182(3)
12.4 Experiments
185(3)
12.4.1 Dataset Description
185(1)
12.4.2 Experimental Results
185(2)
12.4.3 Boosting Slice Features
187(1)
12.5 Discussion
188(5)
References
189(4)
Part V LBP in Various Computer Vision Applications
13 LBP in Different Applications
193(12)
13.1 Detection and Tracking of Objects
193(1)
13.2 Biometrics
194(1)
13.3 Eye Localization and Gaze Tracking
195(1)
13.4 Face Recognition in Unconstrained Environments
195(1)
13.5 Visual Inspection
196(1)
13.6 Biomedical Applications
197(1)
13.7 Texture and Video Texture Synthesis
198(1)
13.8 Steganography and Image Forensics
199(1)
13.9 Video Analysis
199(1)
13.10 Systems for Photo Management and Interactive TV
200(1)
13.11 Embedded Vision Systems and Smart Cameras
201(4)
References
202(3)
Index 205