: Network Disk Download
Content Introduction· · · · · ·
Python Computer vision programming is the authoritative practice guide of Computer vision programming, which relies on the Python language to explain the basic theory and algorithm, and analyzes the object recognition, content-based image search, optical character recognition, optical flow method, tracking, three-dimensional reconstruction, stereo imaging, augmented reality, Attitude estimation, panorama creation, image segmentation, noise reduction, image grouping and other techniques. In addition, the exercises included in the book also allow the reader to consolidate and learn to apply programming knowledge.
"Python Computer Vision Programming" is suitable for readers who have certain programming and mathematical foundations, who want to understand basic theories and algorithms of computer vision, as well as researchers and practitioners in the fields of computer science, signal processing, physics, applied Mathematics and statistics, neurophysiology, and cognitive science.
Author profile ...
Jan Erik Solem
Associate Professor (Mathematics Imaging Group) at Longde University in Sweden, Polar Rose's founder and CTO, Computer vision researcher, Python enthusiast, and technical book writer, often attends international conferences and lectures on computer vision, image analysis, machine intelligence and more. He focuses on 3D reconstruction, variational problems and optimization, image segmentation and recognition, shape analysis, many years of Python computer vision teaching, research and industry application experience, technical blog for http://www.janeriksolem.net. There is also a book computing with Python:an Introduction-Python for science and engineering.
Directory of Python computer vision programming
Recommended Order XI
Foreword XIII
1th. Basic image manipulation and processing 1
1.1 Pil:python Image processing Class library 1
1.1.1 Converting image formats 2
1.1.2 Creating thumbnails 3
1.1.3 copying and pasting an image area 3
1.1.4 adjusting dimensions and rotation 3
1.2 Matplotlib 4
1.2.1 Drawing images, dots, and lines 4
1.2.2 Image outlines and histograms 6
1.2.3 Interactive Callout 7
1.3 NumPy 8
1.3.1 Image Array Representation 8
1.3.2 Grayscale Transformation 9
1.3.3 Image Scaling 11
1.3.4 Histogram equalization 11
1.3.5 Images Average 13
Principal component analysis of 1.3.6 images (PCA) 14
1.3.7 using pickle Module 16
1.4 SciPy 17
1.4.1 Image Blur 18
1.4.2 Image derivative 19
1.4.3 Morphology: Object Count 22
1.4.4 some useful scipy modules 23
1.5 Advanced Example: Image denoising 24
Exercise 28
code example Conventions 29
2nd Chapter Description of local image sub 31
2.1 Harris Corner Point Detector 31
2.2 Sift (scale invariant feature transform) 39
2.2.1 Points of Interest 39
2.2.2 Description Sub 39
2.2.3 detection points of interest 40
2.2.4 Matching Description Sub 43
2.3 Matching a geo-tagged Image 47
2.3.1 Downloading geo-tagged images from Panoramio 47
2.3.2 using local description sub-match 50
2.3.3 Visualization of connected images 52
Exercise 54
3rd image-to-image mapping 57
3.1 Single-sex transformation 57
3.1.1 Direct linear Transformation Algorithm 59
3.1.2 Affine Transformation 60
3.2 Image Warp 61
3.2.1 Images in Images 63
3.2.2 Segmented affine twist 67
3.2.3 Image Registration 70
3.3 Creating panoramas 76
3.3.1 Ransac 77
3.3.2 Robust single-response matrix estimation 78
3.3.3 Stitching Image 81
Exercise 84
4th Camera model and augmented reality 85
4.1 Pinhole camera Model 85
4.1.1 Camera Matrix 86
4.1. Projection of 23-dimensional points 87
4.1.3 decomposition of the camera matrix 89
4.1.4 Computing Camera Center 90
4.2 Camera Calibration 91
4.3 Attitude estimation by plane and marker 93
4.4 Augmented Reality 97
4.4.1 Pygame and Pyopengl 97
4.4.2 from Camera matrix to OpenGL format 98
4.4.3 placing virtual objects in an image 100
4.4.4 Integrated Integration 102
4.4.5 Loading Model 104
Exercise 106
5th Multi-View Geometry 107
5.1 Outer pole Geometry 107
5.1.1 A simple data set 109
5.1.2 drawing three-dimensional data with Matplotlib 111
5.1.3 Calculation F: Eight-point method 112
5.1.4 Outer pole and outer pole line 113
5.2 Calculation of the camera and the three-dimensional structure 116
5.2.13 Angle Split 116
5.2.2 Calculating the camera matrix from a three-dimensional point 118
5.2.3 Calculating the camera matrix from the base matrix 120
5.3 Multi-View rebuild 122
5.3.1 Robust estimation Base matrix 123
5.3.23-dimensional Reconstruction example 125
5.3.3 multi-View Extension Example 129
5.4 Stereoscopic Image 130
Exercise 135
6th. Image Clustering 137
6.1 K-means Cluster 137
6.1.1 scipy Cluster Pack 138
6.1.2 Image Clustering 139
6.1.3 visualizing the image on the main component 140
6.1.4 pixels | Cluster 142
6.2 Hierarchical Clustering 144
6.3 Spectral Clustering 152
Exercise 157
7th. Image Search 159
7.1 Content-based image retrieval 159
7.2 Visual word 160
7.3 Image Index 164
7.3.1 Building a Database 164
7.3.2 Adding an image 165
7.4 Searching for images in the database 167
7.4.1 using indexes to get candidate images 168
7.4.2 using an image to query 169
7.4.3 determining the baseline and drawing the results 171
7.5 Sorting results by using geometric properties 172
7.6 Creating demo programs and Web applications 176
7.6.1 creating a web App with CherryPy 176
7.6.2 Image Search Demo program 176
Exercise 179
8th. Image Content Classification 181
8.1 k Proximity Classification (KNN) 181
8.1.1 a simple two-dimensional example 182
8.1.2 using dense sift as an image feature 185
8.1.3 Image classification: gesture Recognition 187
8.2 Bayesian classifier 190
8.3 Support Vector Machine 195
8.3.1 using LIBSVM 196
8.3.2 again on gesture recognition 198
8.4 Optical Character Recognition 199
8.4.1 Training Classifier 200
8.4.2 Selecting features 200
8.4.3 multi-class support vector machine 201
8.4.4 extracting cells and identifying characters 202
8.4.5 Image Correction 205
Exercise 206
9th Chapter Image Segmentation 209
9.1 Figure cut (graph cut) 209
9.1.1 creating a diagram from an image 211
9.1.2 User Interactive Split 216
9.2 Using clustering to split 218
9.3 Variational Method 224
Exercise 226
10th Chapter OPENCV 227
10.1 OpenCV Python Interface 227
10.2 OpenCV Basic Knowledge 228
10.2.1 Reading and writing images 228
10.2.2 Color Space 228
10.2.3 displaying images and results 229
10.3 Handling Video 232
10.3.1 Video Input 232
10.3.2 reading the video into the NumPy array 234
10.4 Tracking 234
10.4.1 Optical Flow 235
10.4.2 Lucas-kanade Algorithm 237
10.5 More Examples 243
10.5.1 Image Repair 243
10.5.2 Partitioning with watershed transformations 244
10.5.3 using the Hoffmann transform to detect line 245
Exercise 246
Appendix A installation package 247
A.1 NumPy and SciPy 247
a.1.1 Windows 247
a.1.2 Mac OS X 247
a.1.3 Linux 248
A.2 Matplotlib 248
A.3 PiL 248
A.4 LIBSVM 249
A.5 OpenCV 249
a.5.1 Windows and UNIX 249
a.5.2 Mac OS X 249
a.5.3 Linux 250
A.6 vlfeat 250
A.7 Pygame 250
A.8 PYOPENGL 250
a.9 Pydot 251
a.10 Python-graph 251
a.11 Simplejson 252
a.12 Pysqlite 252
a.13 CherryPy 252
Appendix B Image Set 253
B.1 Flickr 253
B.2 Panoramio 254
B.3 Oxford University visual Geometry Group 255
B.4 University of Kentucky identification benchmark Image 255
B.5 Other 256
b.5.1 Prague Texture Segmentation datagenerator with benchmark 256
b.5.2 Microsoft Research Grab cut DataSet 256
b.5.3 Caltech 101 256
b.5.4 Static gesture Database 256
b.5.5 Middlebury Stereo Data Set 256
Appendix C Picture Source 257
C.1 Images from Flickr 257
C.2 Other Images 258
C.3 Illustration 258
References 259
Index 263
: Network Disk Download
Python Computer Vision programming pdf
