Muutke küpsiste eelistusi

E-raamat: Feature Extraction and Image Processing for Computer Vision

3.85/5 (25 hinnangut Goodreads-ist)
(Professor of Electronics and Computer Science, University of Southampton, UK)
  • Formaat: EPUB+DRM
  • Ilmumisaeg: 18-Dec-2012
  • Kirjastus: Academic Press Inc
  • Keel: eng
  • ISBN-13: 9780123978240
Teised raamatud teemal:
  • Formaat - EPUB+DRM
  • Hind: 60,50 €*
  • * 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.
Feature Extraction and Image Processing for Computer VisionSuurem pilt
  • Formaat: EPUB+DRM
  • Ilmumisaeg: 18-Dec-2012
  • Kirjastus: Academic Press Inc
  • Keel: eng
  • ISBN-13: 9780123978240
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. 

After reviewing the human vision system, Nixon (electronics and computer science, U. of Southhampton) and Aguardo (Sportradar) introduce signal processing theory for computer vision and current digital techniques for edge detection within an image, fixed shape matching, and deformable shape analysis. The undergraduate engineering textbook also explains the characterization of objects by boundary, region, and texture descriptions. The third edition adds a chapter on moving object detection and description and an appendix on color images. Academic Press is an imprint of Elsevier. Annotation ©2013 Book News, Inc., Portland, OR (booknews.com)

This book is an essential guide to the implementation of image processing and computer vision techniques, with tutorial introductions and sample code in Matlab. Algorithms are presented and fully explained to enable complete understanding of the methods and techniques demonstrated. As one reviewer noted, "The main strength of the proposed book is the exemplar code of the algorithms."

Fully updated with the latest developments in feature extraction, including expanded tutorials and new techniques, this new edition contains extensive new material on Haar wavelets, Viola-Jones, bilateral filtering, SURF, PCA-SIFT, moving object detection and tracking, development of symmetry operators, LBP texture analysis, Adaboost, and a new appendix on color models. Coverage of distance measures, feature detectors, wavelets, level sets and texture tutorials has been extended.

* Essential reading for engineers and students working in this cutting edge field * Ideal module text and background reference for courses in image processing and computer vision * The only currently-available text to concentrate on feature extraction with working implementation and worked through derivation

Arvustused

"the book is well written and is easy to follow. In fact, the presentation order is the logical order of any actual computer vision system processing pipeline. The authors have done a great job grouping related topics together and touching upon recent techniques." --IAPR Newsletter, October 2013

"The mathematical element is presented in a non-mathematical way thus making the content more accessiblethis edition is a very welcome addition to vision extraction." --IMA.org, August 2013

"All in all, I highly recommend this 600 pager as an introduction for students, and as a reference for practitioners. The latter audience will find an abundance of use references in each chapter" --ComputingReviews.com, April 18, 2013

"After reviewing the human vision system, Nixonand Aguardointroduce signal processing theory for computer vision and current digital techniques for edge detection within an image, fixed shape matching, and deformable shape analysis. The undergraduate engineering textbook also explains the characterization of objects by boundary, region, and texture descriptions." --Reference and Research Book News, February 2013

Muu info

Full coverage of the theory and implementation of feature extraction algorithms and techniques - revised and updated with the latest developments and new tutorials
Preface xi
About the authors xvii
Chapter 1 Introduction
1(36)
1.1 Overview
1(1)
1.2 Human and computer vision
2(2)
1.3 The human vision system
4(8)
1.3.1 The eye
5(3)
1.3.2 The neural system
8(1)
1.3.3 Processing
9(3)
1.4 Computer vision systems
12(7)
1.4.1 Cameras
12(3)
1.4.2 Computer interfaces
15(2)
1.4.3 Processing an image
17(2)
1.5 Mathematical systems
19(11)
1.5.1 Mathematical tools
19(1)
1.5.2 Hello Matlab, hello images!
20(5)
1.5.3 Hello Mathcad!
25(5)
1.6 Associated literature
30(5)
1.6.1 Journals, magazines, and conferences
30(1)
1.6.2 Textbooks
31(3)
1.6.3 The Web
34(1)
1.7 Conclusions
35(1)
1.8 References
35(2)
Chapter 2 Images, Sampling, and Frequency Domain Processing
37(46)
2.1 Overview
37(1)
2.2 Image formation
38(4)
2.3 The Fourier transform
42(7)
2.4 The sampling criterion
49(4)
2.5 The discrete Fourier transform
53(10)
2.5.1 ID transform
53(4)
2.5.2 2D transform
57(6)
2.6 Other properties of the Fourier transform
63(5)
2.6.1 Shift invariance
63(2)
2.6.2 Rotation
65(1)
2.6.3 Frequency scaling
66(1)
2.6.4 Superposition (linearity)
67(1)
2.7 Transforms other than Fourier
68(10)
2.7.1 Discrete cosine transform
68(2)
2.7.2 Discrete Hartley transform
70(1)
2.7.3 Introductory wavelets
71(7)
2.7.4 Other transforms
78(1)
2.8 Applications using frequency domain properties
78(2)
2.9 Further reading
80(1)
2.10 References
81(2)
Chapter 3 Basic Image Processing Operations
83(54)
3.1 Overview
83(1)
3.2 Histograms
84(2)
3.3 Point operators
86(12)
3.3.1 Basic point operations
86(3)
3.3.2 Histogram normalization
89(1)
3.3.3 Histogram equalization
90(3)
3.3.4 Thresholding
93(5)
3.4 Group operations
98(11)
3.4.1 Template convolution
98(3)
3.4.2 Averaging operator
101(2)
3.4.3 On different template size
103(1)
3.4.4 Gaussian averaging operator
104(3)
3.4.5 More on averaging
107(2)
3.5 Other statistical operators
109(14)
3.5.1 Median filter
109(3)
3.5.2 Mode filter
112(2)
3.5.3 Anisotropic diffusion
114(7)
3.5.4 Force field transform
121(1)
3.5.5 Comparison of statistical operators
122(1)
3.6 Mathematical morphology
123(11)
3.6.1 Morphological operators
124(3)
3.6.2 Gray-level morphology
127(1)
3.6.3 Gray-level erosion and dilation
128(2)
3.6.4 Minkowski operators
130(4)
3.7 Further reading
134(1)
3.8 References
134(3)
Chapter 4 Low-Level Feature Extraction (including edge detection)
137(80)
4.1 Overview
138(2)
4.2 Edge detection
140(33)
4.2.1 First-order edge-detection operators
140(21)
4.2.2 Second-order edge-detection operators
161(9)
4.2.3 Other edge-detection operators
170(1)
4.2.4 Comparison of edge-detection operators
171(2)
4.2.5 Further reading on edge detection
173(1)
4.3 Phase congruency
173(7)
4.4 Localized feature extraction
180(19)
4.4.1 Detecting image curvature (corner extraction)
180(13)
4.4.2 Modern approaches: region/patch analysis
193(6)
4.5 Describing image motion
199(13)
4.5.1 Area-based approach
200(4)
4.5.2 Differential approach
204(7)
4.5.3 Further reading on optical flow
211(1)
4.6 Further reading
212(1)
4.7 References
212(5)
Chapter 5 High-Level Feature Extraction: Fixed Shape Matching
217(76)
5.1 Overview
218(2)
5.2 Thresholding and subtraction
220(2)
5.3 Template matching
222(13)
5.3.1 Definition
222(8)
5.3.2 Fourier transform implementation
230(4)
5.3.3 Discussion of template matching
234(1)
5.4 Feature extraction by low-level features
235(8)
5.4.1 Appearance-based approaches
235(3)
5.4.2 Distribution-based descriptors
238(5)
5.5 Hough transform
243(45)
5.5.1 Overview
243(1)
5.5.2 Lines
243(7)
5.5.3 HT for circles
250(5)
5.5.4 HT for ellipses
255(3)
5.5.5 Parameter space decomposition
258(13)
5.5.6 Generalized HT
271(16)
5.5.7 Other extensions to the HT
287(1)
5.6 Further reading
288(1)
5.7 References
289(4)
Chapter 6 High-Level Feature Extraction: Deformable Shape Analysis
293(50)
6.1 Overview
293(1)
6.2 Deformable shape analysis
294(5)
6.2.1 Deformable templates
294(3)
6.2.2 Parts-based shape analysis
297(2)
6.3 Active contours (snakes)
299(26)
6.3.1 Basics
299(2)
6.3.2 The Greedy algorithm for snakes
301(7)
6.3.3 Complete (Kass) snake implementation
308(5)
6.3.4 Other snake approaches
313(1)
6.3.5 Further snake developments
314(4)
6.3.6 Geometric active contours (lcvel-set-based approaches)
318(7)
6.4 Shape skeletonization
325(9)
6.4.1 Distance transforms
325(2)
6.4.2 Symmetry
327(7)
6.5 Flexible shape models-active shape and active appearance
334(4)
6.6 Further reading
338(1)
6.7 References
338(5)
Chapter 7 Object Description
343(56)
7.1 Overview
343(2)
7.2 Boundary descriptions
345(33)
7.2.1 Boundary and region
345(1)
7.2.2 Chain codes
346(3)
7.2.3 Fourier descriptors
349(29)
7.3 Region descriptors
378(17)
7.3.1 Basic region descriptors
378(5)
7.3.2 Moments
383(12)
7.4 Further reading
395(1)
7.5 References
395(4)
Chapter 8 Introduction to Texture Description, Segmentation, and Classification
399(36)
8.1 Overview
399(1)
8.2 What is texture?
400(3)
8.3 Texture description
403(14)
8.3.1 Performance requirements
403(1)
8.3.2 Structural approaches
403(3)
8.3.3 Statistical approaches
406(3)
8.3.4 Combination approaches
409(2)
8.3.5 Local binary patterns
411(6)
8.3.6 Other approaches
417(1)
8.4 Classification
417(12)
8.4.1 Distance measures
417(7)
8.4.2 The k-nearest neighbor rule
424(4)
8.4.3 Other classification approaches
428(1)
8.5 Segmentation
429(2)
8.6 Further reading
431(1)
8.7 References
432(3)
Chapter 9 Moving Object Detection and Description
435(54)
9.1 Overview
435(2)
9.2 Moving object detection
437(14)
9.2.1 Basic approaches
437(5)
9.2.2 Modeling and adapting to the (static) background
442(5)
9.2.3 Background segmentation by thresholding
447(3)
9.2.4 Problems and advances
450(1)
9.3 Tracking moving features
451(23)
9.3.1 Tracking moving objects
451(1)
9.3.2 Tracking by local search
452(3)
9.3.3 Problems in tracking
455(1)
9.3.4 Approaches to tracking
455(2)
9.3.5 Meanshift and Camshift
457(15)
9.3.6 Recent approaches
472(2)
9.4 Moving feature extraction and description
474(9)
9.4.1 Moving (biological) shape analysis
474(2)
9.4.2 Detecting moving shapes by shape matching in image sequences
476(4)
9.4.3 Moving shape description
480(3)
9.5 Further reading
483(1)
9.6 References
484(5)
Chapter 10 Appendix 1: Camera Geometry Fundamentals
489(30)
10.1 Image geometry
489(1)
10.2 Perspective camera
490(1)
10.3 Perspective camera model
491(9)
10.3.1 Homogeneous coordinates and projective geometry
491(5)
10.3.2 Perspective camera model analysis
496(3)
10.3.3 Parameters of the perspective camera model
499(1)
10.4 Affine camera
500(5)
10.4.1 Affine camera model
501(2)
10.4.2 Affine camera model and the perspective projection
503(1)
10.4.3 Parameters of the affine camera model
504(1)
10.5 Weak perspective model
505(2)
10.6 Example of camera models
507(10)
10.7 Discussion
517(1)
10.8 References
518(1)
Chapter 11 Appendix 2: Least Squares Analysis
519(6)
11.1 The least squares criterion
519(2)
11.2 Curve fitting by least squares
521(4)
Chapter 12 Appendix 3: Principal Components Analysis
525(16)
12.1 Principal components analysis
525(1)
12.2 Data
526(1)
12.3 Covariance
526(3)
12.4 Covariance matrix
529(1)
12.5 Data transformation
530(1)
12.6 Inverse transformation
531(1)
12.7 Eigenproblem
532(1)
12.8 Solving the eigenproblem
533(1)
12.9 PC A method summary
533(1)
12.10 Example
534(6)
12.11 References
540(1)
Chapter 13 Appendix 4: Color Images
541(60)
13.1 Color images
542(1)
13.2 Tristimulus theory
542(2)
13.3 Color models
544(56)
13.3.1 The colorimetric equation
544(1)
13.3.2 Luminosity function
545(2)
13.3.3 Perception based color models: the CIE RGB and CIE XYZ
547(15)
13.3.4 Uniform color spaces: CIE LUV and CIE Lab
562(6)
13.3.5 Additive and subtractive color models: RGB and CMY
568(7)
13.3.6 Luminance and chrominance color models: YUV, YIQ, and YCbCr
575(8)
13.3.7 Perceptual color models: HSV and HLS
583(16)
13.3.8 More color models
599(1)
13.4 References
600(1)
Index 601
Mark Nixon is the Professor in Computer Vision at the University of Southampton UK. His research interests are in image processing and computer vision. His team develops new techniques for static and moving shape extraction which have found application in biometrics and in medical image analysis. His team were early workers in automatic face recognition, later came to pioneer gait recognition and more recently joined the pioneers of ear biometrics. With Tieniu Tan and Rama Chellappa, their book Human ID based on Gait is part of the Springer Series on Biometrics and was published in 2005. He has chaired/ program chaired many conferences (BMVC 98, AVBPA 03, IEEE Face and Gesture FG06, ICPR 04, ICB 09, IEEE BTAS 2010) and given many invited talks. Dr. Nixon is a Fellow IET and a Fellow IAPR.
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97801239782406e.html
Märksõnad: