Muutke küpsiste eelistusi

Computer Vision and Image Processing: Fundamentals and Applications [Kõva köide]

3.00/5 (1 hinnangut Goodreads-ist)
(Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, INDIA)
  • Formaat: Hardback, 464 pages, kõrgus x laius: 234x156 mm, kaal: 793 g, 3 Tables, black and white; 257 Illustrations, black and white
  • Ilmumisaeg: 07-Oct-2019
  • Kirjastus: CRC Press
  • ISBN-10: 0367265737
  • ISBN-13: 9780367265731
Teised raamatud teemal:
Computer Vision and Image Processing: Fundamentals and ApplicationsSuurem pilt
  • Formaat: Hardback, 464 pages, kõrgus x laius: 234x156 mm, kaal: 793 g, 3 Tables, black and white; 257 Illustrations, black and white
  • Ilmumisaeg: 07-Oct-2019
  • Kirjastus: CRC Press
  • ISBN-10: 0367265737
  • ISBN-13: 9780367265731
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780367265731.html
Märksõnad:

The book familiarizes readers with fundamental concepts and issues related to computer vision and major approaches that address them. The focus of the book is on image acquisition and image formation models, radiometric models of image formation, image formation in the camera, image processing concepts, concept of feature extraction and feature selection for pattern classification/recognition, and advanced concepts like object classification, object tracking, image-based rendering, and image registration. Intended to be a companion to a typical teaching course on computer vision, the book takes a problem-solving approach.

Preface xiii
Author xv
I Image Formation and Image Processing 1(152)
1 Introduction to Computer Vision and Basic Concepts of Image Formation
3(58)
1.1 Introduction and Goals of Computer Vision
3(3)
1.2 Image Formation and Radiometry
6(15)
1.2.1 Image formation
6(1)
1.2.2 Radiometric quantities
7(7)
1.2.3 Shape from shading
14(5)
1.2.4 Photometric stereo
19(2)
1.3 Geometric Transformation
21(6)
1.3.1 2D transformations
21(4)
1.3.2 3D transformations
25(2)
1.4 Geometric Camera Models
27(26)
1.4.1 Single camera setup of image formation
28(10)
1.4.2 Image formation in a stereo vision setup
38(7)
1.4.3 Basics of stereo correspondence
45(3)
1.4.4 Issues related to accurate disparity map estimation
48(5)
1.5 Image Reconstruction from a Series of Projections
53(7)
1.5.1 Inverse Radon transform - back-projection method
57(1)
1.5.2 Inverse Radon transform - Fourier transform method
58(2)
1.6 Summary
60(1)
2 Image Processing Concepts
61(92)
2.1 Fundamentals of Image Processing
62(15)
2.1.1 Point operations
63(11)
2.1.2 Geometric operations
74(1)
2.1.3 Spatial or neighbourhood operations
74(2)
2.1.4 Operations between images
76(1)
2.2 Image Transforms
77(33)
2.2.1 Discrete fourier transform
81(3)
2.2.2 Discrete cosine transform
84(3)
2.2.3 K-L transform
87(5)
2.2.4 Wavelet transform
92(10)
2.2.5 Curvelet transform
102(1)
2.2.6 Ridgelet transform
103(1)
2.2.7 Shearlet transform
104(4)
2.2.8 Contourlet transform
108(2)
2.3 Image Filtering
110(14)
2.3.1 Spatial domain filtering
111(7)
2.3.2 Frequency domain filtering
118(1)
2.3.3 Homomorphic filtering
119(1)
2.3.4 Wiener filter for image restoration
120(4)
2.4 Colour Image Processing
124(11)
2.4.1 Colour models
125(4)
2.4.2 Colour constancy
129(1)
2.4.3 Colour image enhancement and filtering
130(4)
2.4.4 Colour balancing
134(1)
2.4.5 Pseudo-colouring
134(1)
2.5 Mathematical Morphology
135(7)
2.5.1 Binary morphological operations
136(1)
2.5.2 Applications of binary morphological operations
137(1)
2.5.3 Grayscale morphological operations
138(1)
2.5.4 Distance transformation
139(3)
2.6 Image Segmentation
142(9)
2.6.1 Thresholding
143(2)
2.6.2 Region-based segmentation methods
145(2)
2.6.3 Edge detection-based segmentation
147(1)
2.6.4 Deformable models for image segmentation
148(3)
2.7 Summary
151(2)
II Image Features 153(58)
3 Image Descriptors and Features
155(56)
3.1 Texture Descriptors
156(9)
3.1.1 Texture representation methods
157(3)
3.1.2 Gabor filter
160(2)
3.1.3 MPEG-7 homogeneous texture descriptor
162(2)
3.1.4 Local binary patterns
164(1)
3.2 Colour Features
165(2)
3.3 Edge Detection
167(16)
3.3.1 Gradient-based methods
168(7)
3.3.2 Laplacian of Gaussian operator
175(2)
3.3.3 Difference of Gaussian operator
177(1)
3.3.4 Canny edge detector
177(2)
3.3.5 Hough transform for detection of a line and other shapes
179(4)
3.4 Object Boundary and Shape Representations
183(9)
3.4.1 Chain code and shape number
183(2)
3.4.2 Fourier descriptors
185(1)
3.4.3 Boundary representation by B-spline curves
186(3)
3.4.4 MPEG-7 contour-based shape descriptor
189(1)
3.4.5 Moment invariants
190(1)
3.4.6 Angular radial transform shape descriptor
191(1)
3.5 Interest or Corner Point Detectors
192(6)
3.5.1 SUSAN edge and corner point detector
193(1)
3.5.2 Moravec corner detector
194(1)
3.5.3 Harris corner detector
195(3)
3.5.4 Hessian corner detector
198(1)
3.6 Histogram of Oriented Gradients
198(2)
3.7 Scale Invariant Feature Transform
200(6)
3.8 Speeded up Robust Features
206(1)
3.9 Saliency
207(2)
3.10 Summary
209(2)
III Recognition 211(62)
4 Fundamental Pattern Recognition Concepts
213(60)
4.1 Introduction to Pattern Recognition
214(4)
4.2 Linear Regression
218(3)
4.3 Basic Concepts of Decision Functions
221(5)
4.3.1 Linear discriminant functions for pattern classification
223(1)
4.3.2 Minimum distance classifier
224(2)
4.4 Elementary Statistical Decision Theory
226(2)
4.5 Gaussian Classifier
228(3)
4.6 Parameter Estimation
231(4)
4.6.1 Parametric approaches
232(1)
4.6.2 Non-parametric approaches
233(2)
4.7 Clustering for Knowledge Representation
235(1)
4.8 Dimension Reduction
235(6)
4.8.1 Unsupervised linear dimension reduction
236(2)
4.8.2 Supervised linear dimension reduction
238(2)
4.8.3 Semi-supervised linear dimension reduction
240(1)
4.9 Template Matching
241(7)
4.9.1 Finding patterns in an image
241(1)
4.9.2 Shape similarity measurement by Hausdorff distance
242(2)
4.9.3 Matching of temporal motion trajectories
244(4)
4.10 Artificial Neural Network for Pattern Classification
248(17)
4.10.1 Simple ANN for pattern classification
252(5)
4.10.2 Supervised learning
257(3)
4.10.3 Unsupervised learning
260(5)
4.11 Convolutional Neural Networks
265(6)
4.11.1 Convolutional layer
267(1)
4.11.2 Pooling layer
268(1)
4.11.3 Fully connected layer
269(2)
4.12 Autoencoder
271(1)
4.13 Summary
272(1)
IV Applications 273(150)
5 Applications of Computer Vision
275(148)
5.1 Machine Learning Algorithms and their Applications in Medical Image Segmentation
276(30)
5.1.1 Clustering for image segmentation
278(6)
5.1.2 Supervised clustering for image segmentation
284(4)
5.1.3 Graph partitioning methods
288(3)
5.1.4 Image segmentation by neural networks
291(3)
5.1.5 Deformable models for image segmentation
294(6)
5.1.6 Probabilistic models for image segmentation
300(1)
5.1.7 Basics of MRF
301(4)
5.1.8 Conclusion
305(1)
5.2 Motion Estimation and Object Tracking
306(23)
5.2.1 Overview of a video surveillance system
307(2)
5.2.2 Background subtraction and modeling
309(2)
5.2.3 Object tracking
311(2)
5.2.4 Kanade-Lucas-Tomasi tracker
313(1)
5.2.5 Mean shift tracking
314(2)
5.2.6 Blob matching
316(1)
5.2.7 Tracking with Kalman filter
317(3)
5.2.8 Tracking with particle filter
320(2)
5.2.9 Multiple camera-based object tracking
322(1)
5.2.10 Motion estimation by optical flow
323(4)
5.2.11 MPEG-7 motion trajectory representation
327(1)
5.2.12 Conclusion
328(1)
5.3 Face and Facial Expression Recognition
329(9)
5.3.1 Face recognition by eigenfaces and fisherfaces
330(1)
5.3.2 Facial expression recognition system
331(1)
5.3.3 Face model-based FER
332(2)
5.3.4 Facial expression parametrization
334(1)
5.3.5 Major challenges in recognizing facial expressions
335(3)
5.3.6 Conclusion
338(1)
5.4 Gesture Recognition
338(12)
5.4.1 Major challenges of hand gesture recognition
339(2)
5.4.2 Vision-based hand gesture recognition system
341(9)
5.4.3 Conclusion
350(1)
5.5 Image Fusion
350(10)
5.5.1 Image fusion methods
353(4)
5.5.2 Performance evaluation metrics
357(2)
5.5.3 Conclusion
359(1)
5.6 Programming Examples
360(63)
Bibliography 423(22)
Index 445
Prof. Manas Kamal Bhuyan received a Ph.D. degree in electronics and communication engineering from the India Institute of Technology (IIT) Guwahati, India. He was with the School of Information Technology and Electrical Engineering, University of Queensland, St. Lucia, QLD, Australia, where he was involved in postdoctoral research. He was also a Researcher with the SAFE Sensor Research Group, NICTA, Brisbane, QLD, Australia. He was an Assistant Professor with the Department of Electrical Engineering, IIT Roorkee, India and Jorhat Engineering College, Assam, India. In 2014, he was a Visiting Professor with Indiana University and Purdue University, Indiana, USA. He is currently a Professor with the Department of Electronics and Electrical Engineering, IIT Guwahati, and Associate Dean of Infrastructure, Planning and Management, IIT Guwahati. His current research interests include image/video processing, computer vision, machine Learning and human computer interactions (HCI), virtual reality and augmented reality. Dr. Bhuyan was a recipient of the National Award for Best Applied Research/Technological Innovation, which was presented by the Honorable President of India, the Prestigious Fullbright-Nehru Academic and Professional Excellence Fellowship, and the BOYSCAST Fellowship. He is an IEEE senior member. He has almost 25 years of industry, teaching, and research experience.