About This BookCreate impressive applications with OpenCV and PythonFamiliarize yourself with advanced machine learning conceptsHarness the power of computer vision with this easy-to-follow guideWho This Book Is ForIntended for novices to the world of OpenCV and computer vision, as well as OpenCV veterans who want to learn about what's new in OpenCV 3, this book is useful as a reference for experts and a training manual for beginners, or for anybody who wants to familiarize themselves with the concepts of object classification and detection in simple and understandable terms. Basic knowledge of Python and programming concepts is required, although the book has an easy learning curve both from a theoretical and coding point of view.What You Will LearnInstall and familiarize yourself with OpenCV 3's Python APIGrasp the basics of image processing and video analysisIdentify and recognize objects in images and videosDetect and recognize faces using OpenCVTrain and use your own object classifiersLearn about machine learning concepts in a computer vision contextWork with artificial neural networks using OpenCVDevelop your own real-life computer vision applicationsIn Detail
Learning OpenCV 3 Computer Vision with Python, Second Edition, takes you through building a theoretical foundation for image processing and video analysis and progress to the concepts of classification through machine learning, acquiring the technical know-how that will allow you to create and use object detectors and classifiers, and even track objects in movies or video camera feeds.
Finally, this journey ends at the world of artificial neural networks, along with the development of a hand-written digit recognition application.
Author(s): Joe Minichino
Edition: 2
Publisher: Packt Publishing
Year: 2015
Language: English
Pages: 266
Cover
Copyright
Credits
About the Authors
About the Reviewers
www.PacktPub.com
Table of Contents
Preface
Chapter 1: Setting Up OpenCV
Choosing and using the right setup tools
Installation on Windows
Using binary installers (no support for depth cameras)
Using CMake and compilers
Installing on OS X
Using MacPorts with ready-made packages
Using MacPorts with your own custom packages
Using Homebrew with ready-made packages (no support for depth cameras)
Using Homebrew with your own custom packages
Installation on Ubuntu and its derivatives
Using the Ubuntu repository (no support for depth cameras)
Building OpenCV from a source
Installation on other Unix-like systems
Installing the Contrib modules
Running samples
Finding documentation, help, and updates
Summary
Chapter 2: Handling Files, Cameras, and GUIs
Basic I/O scripts
Reading/writing an image file
Converting between an image and raw bytes
Accessing image data with numpy.array
Reading/writing a video file
Capturing camera frames
Displaying images in a window
Displaying camera frames in a window
Project Cameo (face tracking and image manipulation)
Cameo – an object-oriented design
Abstracting a video stream with managers.CaptureManager
Abstracting a window and keyboard with managers.WindowManager
Applying everything with cameo.Cameo
Summary
Chapter 3: Processing Images with OpenCV 3
Converting between different color spaces
A quick note on BGR
The Fourier Transform
High pass filter
Low pass filter
Creating modules
Edge detection
Custom kernels – getting convoluted
Modifying the application
Edge detection with Canny
Contour detection
Contours – bounding box, minimum area rectangle, and minimum enclosing circle
Contours – convex contours and the Douglas-Peucker algorithm
Line and circle detection
Line detection
Circle detection
Detecting shapes
Summary
Chapter 4: Depth Estimation and Segmentation
Creating modules
Capturing frames from a depth camera
Creating a mask from a disparity map
Masking a copy operation
Depth estimation with a normal camera
Object segmentation using the Watershed and GrabCut algorithms
Example of foreground detection with GrabCut
Image segmentation with the Watershed algorithm
Summary
Chapter 5: Detecting and Recognizing Faces
Conceptualizing Haar cascades
Getting Haar cascade data
Using OpenCV to perform face detection
Performing face detection on a still image
Performing face detection on a video
Performing face recognition
Generating the data for face recognition
Recognizing faces
Preparing the training data
Loading the data and recognizing faces
Performing an Eigenfaces recognition
Performing face recognition with Fisherfaces
Performing face recognition with LBPH
Discarding results with confidence score
Summary
Chapter 6: Retrieving Images and Searching Using Image Descriptors
Feature detection algorithms
Defining features
Detecting features – corners
Feature extraction and description using DoG and SIFT
Anatomy of a keypoint
Feature extraction and detection using Fast Hessian and SURF
ORB feature detection and feature matching
FAST
BRIEF
Brute-Force matching
Feature matching with ORB
Using K-Nearest Neighbors matching
FLANN-based matching
FLANN matching with homography
A sample application – tattoo forensics
Saving image descriptors to file
Scanning for matches
Summary
Chapter 7: Detecting and Recognizing Objects
Object detection and recognition techniques
HOG descriptors
The scale issue
The location issue
Non-maximum (or non-maxima) suppression
Support vector machines
People detection
Creating and training an object detector
Bag-of-words
BOW in computer vision
Detecting cars
What did we just do?
SVM and sliding windows
Example – car detection in a scene
Dude, where's my car?
Summary
Chapter 8: Tracking Objects
Detecting moving objects
Basic motion detection
Background subtractors – KNN, MOG2, and GMG
Meanshift and CAMShift
Color histograms
The calcHist function
The calcBackProject function
In summary
Back to the code
CAMShift
The Kalman filter
Predict and update
An example
A real-life example – tracking pedestrians
The application workflow
A brief digression – functional versus object-oriented programming
The Pedestrian class
The main program
Where do we go from here?
Summary
Chapter 9: Neural Networks with OpenCV – an Introduction
Artificial neural networks
Neurons and perceptrons
The structure of an ANN
Network layers by example
The input layer
The output layer
The hidden layer
ANNs in OpenCV
ANN-imal classification
Training epochs
Handwritten digit recognition with ANNs
MNIST – the handwritten digit database
Customized training data
The initial parameters
The input layer
The hidden layer
The output layer
Training epochs
Other parameters
Mini-libraries
The main file
Possible improvements and potential applications
Improvements
Potential applications
Summary
To boldly go…
Index
