Muutke küpsiste eelistusi

E-raamat: Advanced Image and Video Processing Using MATLAB

, , , , ,
Teised raamatud teemal:
  • Formaat - EPUB+DRM
  • Hind: 74,09 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Advanced Image and Video Processing Using MATLABSuurem pilt
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

This book offers a comprehensive introduction to advanced methods for image and video analysis and processing. It covers deraining, dehazing, inpainting, fusion, watermarking and stitching. It describes techniques for face and lip recognition,  facial expression recognition, lip reading in videos, moving object tracking, dynamic scene classification, among others.





The book combines the latest machine learning methods with computer vision applications, covering topics such as event recognition based on deep learningdynamic scene classification based on topic model, person re-identification based on metric learning and behavior analysis. It also offers a systematic introduction to image evaluation criteria showing how to use them in different experimental contexts.





The book offers an example-based practical guide to researchers, professionals and graduate students dealing with advanced problems in image analysis and computer vision.
Part I The Basic Concepts
1 Introduction
3(24)
1.1 Basic Concepts and Terminology
3(6)
1.1.1 Digital Image and Digital Video
3(3)
1.1.2 Image Processing
6(1)
1.1.3 Image Analysis
6(2)
1.1.4 Video Analysis
8(1)
1.2 Image and Video Analysis
9(5)
1.2.1 Image and Video Scene Segmentation
9(1)
1.2.2 Image and Video Feature Description
10(2)
1.2.3 Object Recognition in Images/Videos
12(1)
1.2.4 Scene Description and Understanding
13(1)
1.3 Examples of Advanced Applications
14(9)
1.3.1 Image Correction
14(1)
1.3.2 Image Fusion
15(1)
1.3.3 Digital Image Inpainting
15(1)
1.3.4 Image Stitching
16(1)
1.3.5 Digital Watermarking
17(1)
1.3.6 Visual Object Recognition
18(2)
1.3.7 Object Tracking
20(1)
1.3.8 Dynamic Scene Classification
21(1)
1.3.9 Pedestrian Re-identification
22(1)
1.3.10 Lip Recognition in Video
22(1)
References
23(4)
2 Matlab Functions of Image and Video
27(38)
2.1 Introduction to MATLAB for Image and Video
27(1)
2.2 Basic Elements of MATLAB
28(7)
2.2.1 Working Environment
28(1)
2.2.2 Data Types
29(3)
2.2.3 Array and Matrix Indexing in MATLAB
32(2)
2.2.4 Standard Arrays
34(1)
2.2.5 Command-Line Operations
34(1)
2.3 Programming Tools: Scripts and Functions
35(6)
2.3.1 M-Files
35(1)
2.3.2 Operators
36(2)
2.3.3 Important Variables and Constants
38(1)
2.3.4 Number Representation
38(1)
2.3.5 Flow Control
39(2)
2.3.6 Input and Output
41(1)
2.4 Graphics and Visualization
41(5)
2.5 The Image Processing Toolbox
46(12)
2.5.1 The Image Processing Toolbox: An Overview
46(1)
2.5.2 Essential Functions and Features
47(5)
2.5.3 Displaying Information About an Image File
52(1)
2.5.4 Reading an Image File
52(1)
2.5.5 Data Classes and Data Conversions
53(2)
2.5.6 Displaying the Contents of an Image
55(2)
2.5.7 Exploring the Contents of an Image
57(1)
2.5.8 Writing the Resulting Image onto a File
58(1)
2.6 Video Processing in MATLAB
58(5)
2.6.1 Reading Video Files
59(1)
2.6.2 Processing Video Files
59(1)
2.6.3 Playing Video Files
60(1)
2.6.4 Writing Video Files
61(1)
2.6.5 Basic Digital Video Manipulation in MATLAB
62(1)
References
63(2)
3 Image and Video Segmentation
65(48)
3.1 Introduction
65(1)
3.2 Threshold Segmentation
66(8)
3.2.1 Global Threshold Image Segmentation
68(1)
3.2.2 Local Dynamic Threshold Segmentation
69(5)
3.3 Region-Based Segmentation
74(14)
3.3.1 Region Growing
74(4)
3.3.2 Region Splitting and Merging
78(10)
3.4 Segmentation Based on Partial Differential Equation
88(6)
3.5 Image Segmentation Based on Clustering
94(3)
3.6 Image Segmentation Method Based on Graph Theory
97(10)
3.6.1 Introduction
97(2)
3.6.2 GraphCut and Improved Image Segmentation Method
99(8)
3.7 Video Motion Region Extraction Method Based on Cumulative Difference
107(4)
References
111(2)
4 Feature Extraction and Representation
113(48)
4.1 Introduction
113(2)
4.2 Histogram-Based Features
115(6)
4.2.1 Grayscale Histogram
115(2)
4.2.2 Histograms of Oriented Gradients
117(4)
4.3 Texture Features
121(14)
4.3.1 Haralick Texture Descriptors
122(4)
4.3.2 Wavelet Texture Descriptors
126(5)
4.3.3 LBP Texture Descriptors
131(4)
4.4 Corner Feature Extraction
135(9)
4.4.1 Moravec Algorithm
135(2)
4.4.2 Harris Corner Detection Operator
137(4)
4.4.3 SUSAN Corner Detection Algorithm
141(3)
4.5 Local Invariant Feature Point Extraction
144(14)
4.5.1 Local Invariant Point Feature of SURF
145(4)
4.5.2 SIFT Scale-Invariant Feature Algorithm
149(9)
References
158(3)
Part II Advances in Image Processing
5 Image Correction
161(48)
5.1 Introduction
161(1)
5.2 Noise Reduction Using Spatial-Domain Techniques
161(12)
5.2.1 Selected Noise Probability Density Functions
162(6)
5.2.2 Filtering
168(5)
5.3 Image Deblurring
173(7)
5.3.1 The Restoration of Defocus Blurred Image
174(2)
5.3.2 Restoration of Motion Blurred Image
176(4)
5.4 Fisheye Distortion Correction Using Spherical Coordinates Model
180(6)
5.5 Skew Correction of Text Images
186(5)
5.5.1 Feature Analysis of Text Images
187(1)
5.5.2 The Basic Idea of Hough Transform
187(1)
5.5.3 The Implementation Steps of Text Images Skew Correction
188(3)
5.6 Image Dehazing Correction
191(9)
5.6.1 Single Image Dehazing
191(1)
5.6.2 Dark Channel Prior
192(2)
5.6.3 Implementation Steps of DCP
194(1)
5.6.4 Refine Transmission Map Using Soft Matting
195(5)
5.7 Image Deraining Correction
200(6)
5.7.1 Related Work
200(1)
5.7.2 Single Image De-rain with Deep Detail Network
200(3)
5.7.3 Implementation of Image Deraining with Deep Network
203(3)
References
206(3)
6 Image Inpainting
209(24)
6.1 Introduction
209(2)
6.1.1 Structure Oriented Image Inpainting Technology
210(1)
6.1.2 Texture-Based Image Inpainting Technology
211(1)
6.2 The Principle of Image Inpainting
211(2)
6.3 Variational PDE-Based Image Inpainting
213(9)
6.3.1 Image Inpainting Algorithm Based on Total Variational Model
214(5)
6.3.2 Image Inpainting Based on CDD Model
219(3)
6.4 Exemplar-Based Image Inpainting Algorithm
222(8)
References
230(3)
7 Image Fusion
233(38)
7.1 Introduction
233(1)
7.2 Fusion Categories
234(9)
7.2.1 Multi-view Fusion
234(2)
7.2.2 Multimodal Fusion
236(4)
7.2.3 Multi-temporal Fusion
240(2)
7.2.4 Multi-focus Fusion
242(1)
7.3 Image Fusion Schemes
243(5)
7.4 Image Fusion Using Wavelet Transform
248(5)
7.4.1 Basis of Wavelet Transform
248(1)
7.4.2 Discrete Dyadic Wavelet Transform of Image and Its Mallat Algorithm
249(1)
7.4.3 Steps of Implementation
250(3)
7.5 Region-Based Image Fusion
253(7)
7.5.1 Basic Framework of Regional Integration
254(1)
7.5.2 The Strategy of Regional Joint Representation
255(1)
7.5.3 The Rules of Fusion
256(1)
7.5.4 Wavelet Fusion of Regional Variance
256(4)
7.6 Image Fusion Using Fuzzy Dempster-Shafer Evidence Theory
260(3)
7.7 Image Quality and Fusion Evaluations
263(5)
7.7.1 Subjective Evaluation of Image Fusion
264(1)
7.7.2 Objective Evaluation of Image Fusion
264(4)
References
268(3)
8 Image Stitching
271(58)
8.1 Introduction
271(1)
8.2 Image Stitching Based on Region
272(18)
8.2.1 Image Stitching Based on Ratio Matching
273(3)
8.2.2 Image Stitching Based on Line and Plane Feature
276(7)
8.2.3 Image Stitching Based on FFT
283(7)
8.3 Images Stitching Based on Feature Points
290(30)
8.3.1 SIFT Feature Points Detection
290(7)
8.3.2 Image Stitching Based on Harris Feature Points
297(7)
8.3.3 Auto-Sorting for Image Sequence
304(3)
8.3.4 Harris Point Registration Based on RANSAC Algorithm
307(13)
8.4 Panoramic Image Stitching
320(7)
References
327(2)
9 Image Watermarking
329(22)
9.1 Introduction
329(5)
9.2 Fragile Watermarking Based on Spatial Domain
334(2)
9.3 Robust Watermarking Based on DCT
336(8)
9.4 Semi-fragile Watermarking Based on DWT
344(5)
References
349(2)
10 Visual Object Recognition
351(40)
10.1 Face Recognition Based on Locality Preserving Projections
351(24)
10.2 Facial Expression Recognition Using PCA
375(5)
10.3 Extraction and Recognition of Characters in Pictures
380(7)
References
387(4)
Part III Advances in Video Processing and then Associated
Chapters
11 Visual Object Tracking
391(38)
11.1 Adaptive Background Modeling by Using a Mixture of Gaussians
391(5)
11.2 Object Tracking Based on Ransac
396(5)
11.3 Object Tracking Based on MeanShift
401(8)
11.3.1 Description of the Object Model
402(1)
11.3.2 A Description of the Candidate Model
402(1)
11.3.3 Similarity Function
403(1)
11.3.4 Object Location
403(6)
11.4 Object Tracking Based on Particle Filter
409(9)
11.4.1 Prior Knowledge of the Goal
410(1)
11.4.2 System State Transition
410(1)
11.4.3 System Observation
411(1)
11.4.4 Posterior Probability Calculation
412(1)
11.4.5 Particle Resampling
412(1)
11.4.6 Implementation Steps
413(5)
11.5 Multiple Object Tracking
418(9)
References
427(2)
12 Dynamic Scene Classification Based on Topic Models
429(46)
12.1 Overview
429(1)
12.2 Introduction to the Topic Models
430(9)
12.2.1 LDA Model
430(3)
12.2.2 TMBP Model Based on Factor Graph
433(3)
12.2.3 TMBP Model Fusing Prior Knowledge
436(3)
12.3 Dynamic Scene Classification Based on TMBP
439(12)
12.4 Behavior Recognition Based on LDA Topic Model
451(24)
13 Image Understanding-Person Re-identification
475(38)
13.1 Introduction
475(2)
13.2 Person Re-ID Scenarios
477(1)
13.3 Methodology
478(2)
13.4 Public Datasets and Evaluation Metrics in Person Re-identification
480(4)
13.4.1 Public Datasets
480(3)
13.4.2 Evaluation Metrics
483(1)
13.5 Classic Feature Representations for Person Re-identification
484(17)
13.5.1 Salient Color Names
484(3)
13.5.2 Local Maximal Occurrence Representation
487(14)
13.6 An Example of Metric Learning Based Person Re-identification Method-XQDA
501(10)
References
511(2)
14 Image and Video Understanding Based on Deep Learning
513(42)
14.1 Introduction
513(2)
14.2 Model Analysis of CNN
515(7)
14.2.1 Basic Modules of CNN
515(1)
14.2.2 Convolution and Pooling
515(1)
14.2.3 Activation Function
516(1)
14.2.4 Softmax Classifier and Cost Function
517(2)
14.2.5 Learning Algorithm
519(2)
14.2.6 Dropout
521(1)
14.2.7 Batch Normalization
522(1)
14.3 Typical CNN Models
522(9)
14.3.1 LeNet
522(1)
14.3.2 AlexNet
523(1)
14.3.3 GoogLeNet
524(4)
14.3.4 VGGNet
528(2)
14.3.5 ResNet
530(1)
14.4 Deep Learning Model for Lip Recognition Instance
531(8)
14.4.1 Testing Dataset
531(1)
14.4.2 Deep Network Training
532(4)
14.4.3 Code Analysis
536(3)
14.5 Deep CNN Architecture for Event Recognition Instance
539(14)
14.5.1 Testing Dataset
539(1)
14.5.2 Deep Feature Extraction
540(1)
14.5.3 Spatial-Temporal Feature Fusion
540(1)
14.5.4 Fisher Vector Encoding
541(1)
14.5.5 Code Analysis
542(11)
References
553(2)
Appendix: Common Evaluation Criterion 555
 





Shengrong Gong received his M.S. degree from Harbin Institute of Technology in 1993, and his Ph.D degree from Beihang University in 2001. He is the dean of School of Computer Science and Engineering, Changshu Institute of Science and Technology, and also a professor and doctoral supervisor. His research interests are image and video processing, pattern recognition, and computer vision.





 





Chunping Liu received her Ph.D degree in pattern recognition and artificial intelligence from Nanjing University of Science & Technology in 2002. She is now a professor of School of Computer Science & Technology, Soochow University. Her research interests include computer vision, image analysis and recognition, in particular in the domains of visual saliency detection, object detection and recognition and scene understanding.





 





Yi Ji received her M.S. Degree from National University of Singapore, Singapore and Ph.D. degree from INSA de Lyon, France. She is now an associate professor in School of Computer Science & Technology of Soochow University. Her research areas are 3D action recognition and complex scene understanding.





 





Baojiang Zhong received the B.S. degree in mathematics from Nanjing Normal University, China in 1995, the M.S. degree in mathematics, and the Ph.D. degree in mechanical and electrical engineering from Nanjing University of Aeronautics and Astronautics (NUAA), China in 1998 and 2006, respectively. From 1998 to 2009, he was on the faculty of the Department of Mathematics of NUAA and reached the rank of Associate Professor. During 2007 to 2008, he was also a Research Scientist with the Temasek Laboratories, Nanyang Technological University, Singapore. In 2009, he joined the School of Computer Science and Technology, Soochow University, China, where he is currently a Full Professor. His research interests include computer vision, image processing, and numerical linear algebra.





 





Yonggang Li received the M.S. degree from Xian Polytechnic University in 2005. He is currently pursuing the Ph.D degree in School of Computer Science and Technology, Soochow University. He is a lecturer of College of mathematics physics and information engineering, Jiaxing University. His research interests include computer vision, image and video processing, and pattern recognition.





 





Husheng Dong received his M.S. degree from School of Computer Science & Technology, Soochow University in 2008, and he is pursuing the Ph.D degree currently. He is also a lecturer of Suzhou Institute of Trade & Commerce. His research interest includes computer vision, image and video processing, and machine learning.





 
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97833197722336e.html