Programming Computer Vision with Python by Solem, Jan Erik -- Read -- Imperial Library of Trantor

Index

Programming Computer Vision with Python Preface

Prerequisites and Overview

What You Need to Know What You Will Learn Chapter Overview

Introduction to Computer Vision Python and NumPy Notation and Conventions Using Code Examples How to Contact Us Safari® Books Online Acknowledgments

1. Basic Image Handling and Processing

1.1 PIL—The Python Imaging Library

Convert Images to Another Format Create Thumbnails Copy and Paste Regions Resize and Rotate

1.2 Matplotlib

Plotting Images, Points, and Lines Image Contours and Histograms Interactive Annotation

1.3 NumPy

Array Image Representation Graylevel Transforms Image Resizing Histogram Equalization Averaging Images PCA of Images Using the Pickle Module

1.4 SciPy

Blurring Images Image Derivatives Morphology—Counting Objects Useful SciPy Modules

Reading and writing .mat files Saving arrays as images

1.5 Advanced Example: Image De-Noising Exercises Conventions for the Code Examples

2. Local Image Descriptors

2.1 Harris Corner Detector

Finding Corresponding Points Between Images

2.2 SIFT—Scale-Invariant Feature Transform

Interest Points Descriptor Detecting Interest Points Matching Descriptors

2.3 Matching Geotagged Images

Downloading Geotagged Images from Panoramio Matching Using Local Descriptors Visualizing Connected Images

Exercises

3. Image to Image Mappings

3.1 Homographies

The Direct Linear Transformation Algorithm Affine Transformations

3.2 Warping Images

Image in Image Piecewise Affine Warping Registering Images

3.3 Creating Panoramas

RANSAC Robust Homography Estimation Stitching the Images Together

Exercises

4. Camera Models and Augmented Reality

4.1 The Pin-Hole Camera Model

The Camera Matrix Projecting 3D Points Factoring the Camera Matrix Computing the Camera Center

4.2 Camera Calibration

A Simple Calibration Method

4.3 Pose Estimation from Planes and Markers 4.4 Augmented Reality

PyGame and PyOpenGL From Camera Matrix to OpenGL Format Placing Virtual Objects in the Image Tying It All Together Loading Models

Exercises

5. Multiple View Geometry

5.1 Epipolar Geometry

A Sample Data Set Plotting 3D Data with Matplotlib Computing F—The Eight Point Algorithm The Epipole and Epipolar Lines

5.2 Computing with Cameras and 3D Structure

Triangulation Computing the Camera Matrix from 3D Points Computing the Camera Matrix from a Fundamental Matrix

The uncalibrated case—projective reconstruction The calibrated case—metric reconstruction

5.3 Multiple View Reconstruction

Robust Fundamental Matrix Estimation 3D Reconstruction Example Extensions and More Than Two Views

More views Bundle adjustment Self-calibration

5.4 Stereo Images

Computing Disparity Maps

Exercises

6. Clustering Images

6.1 K-Means Clustering

The SciPy Clustering Package Clustering Images Visualizing the Images on Principal Components Clustering Pixels

6.2 Hierarchical Clustering

Clustering Images

6.3 Spectral Clustering Exercises

7. Searching Images

7.1 Content-Based Image Retrieval

Inspiration from Text Mining—The Vector Space Model

7.2 Visual Words

Creating a Vocabulary

7.3 Indexing Images

Setting Up the Database Adding Images

7.4 Searching the Database for Images

Using the Index to Get Candidates Querying with an Image Benchmarking and Plotting the Results

7.5 Ranking Results Using Geometry 7.6 Building Demos and Web Applications

Creating Web Applications with CherryPy Image Search Demo

Exercises

8. Classifying Image Content

8.1 K-Nearest Neighbors

A Simple 2D Example Dense SIFT as Image Feature Classifying Images—Hand Gesture Recognition

8.2 Bayes Classifier

Using PCA to Reduce Dimensions

8.3 Support Vector Machines

Using LibSVM Hand Gesture Recognition Again

8.4 Optical Character Recognition

Training a Classifier Selecting Features Multi-Class SVM Extracting Cells and Recognizing Characters Rectifying Images

Exercises

9. Image Segmentation

9.1 Graph Cuts

Graphs from Images Segmentation with User Input

9.2 Segmentation Using Clustering 9.3 Variational Methods Exercises

10. OpenCV

10.1 The OpenCV Python Interface 10.2 OpenCV Basics

Reading and Writing Images Color Spaces Displaying Images and Results

10.3 Processing Video

Video Input Reading Video to NumPy Arrays

10.4 Tracking

Optical Flow The Lucas-Kanade Algorithm

Using the tracker Using generators

10.5 More Examples

Inpainting Segmentation with the Watershed Transform Line Detection with a Hough Transform

Exercises

A. Installing Packages

A.1 NumPy and SciPy

Windows Mac OS X Linux

A.2 Matplotlib A.3 PIL A.4 LibSVM A.5 OpenCV

Windows and Unix Mac OS X Linux

A.6 VLFeat A.7 PyGame A.8 PyOpenGL A.9 Pydot A.10 Python-graph A.11 Simplejson A.12 PySQLite A.13 CherryPy

B. Image Datasets

B.1 Flickr B.2 Panoramio B.3 Oxford Visual Geometry Group B.4 University of Kentucky Recognition Benchmark Images B.5 Other

Prague Texture Segmentation Datagenerator and Benchmark MSR Cambridge Grab Cut Dataset Caltech 101 Static Hand Posture Database Middlebury Stereo Datasets

C. Image Credits

C.1 Images from Flickr C.2 Other Images C.3 Illustrations

D. References E. About the Author Index About the Author Colophon Copyright

← Prev
Back
Next →

← Prev
Back
Next →