Now in its third edition, this is the original book on OpenCV's Python bindings. Readers will learn a great range of techniques and algorithms, from the classics to the state-of-the-art, and from geometry to machine learning. All of this is in aid of solving practical computer vision problems in well-built applications.

• Cover
• Title Page
• Copyright and Credits
• Dedication
• About Packt
• Contributors
• Table of Contents
• Preface
• Chapter 1: Setting Up OpenCV
  • Technical requirements
  • What's new in OpenCV 4
  • Choosing and using the right setup tools
    • Installation on Windows
      • Using a ready-made OpenCV package
      • Building OpenCV from source
    • Installation on macOS
      • Using Homebrew with ready-made packages
      • Using Homebrew with your own custom packages
    • Installation on Debian, Ubuntu, Linux Mint, and similar systems
      • Using a ready-made OpenCV package
      • Building OpenCV from source
    • Installation on other Unix-like systems
  • Running samples
  • Finding documentation, help, and updates
  • Summary
• Chapter 2: Handling Files, Cameras, and GUIs
  • Technical requirements
  • 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 an image 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
  • Technical requirements
  • Converting images between different color models
    • Light is not paint 
  • Exploring the Fourier transform
    • HPFs and LPFs
  • Creating modules
  • Edge detection
  • Custom kernels – getting convoluted
  • Modifying the application
  • Edge detection with Canny
  • Contour detection
    • Bounding box, minimum area rectangle, and minimum enclosing circle
    • Convex contours and the Douglas-Peucker algorithm
  • Detecting lines, circles, and other shapes
    • Detecting lines
    • Detecting circles
    • Detecting other shapes
  • Summary
• Chapter 4: Depth Estimation and Segmentation
  • Technical requirements
  • Creating modules
  • Capturing frames from a depth camera
  • Converting 10-bit images to 8-bit
  • Creating a mask from a disparity map
  • Modifying the application
  • Depth estimation with a normal camera
  • Foreground detection with the GrabCut algorithm
  • Image segmentation with the Watershed algorithm
  • Summary
• Chapter 5: Detecting and Recognizing Faces
  • Technical requirements
  • 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
      • Loading the training data for face recognition
      • Performing face recognition with Eigenfaces
      • Performing face recognition with Fisherfaces
      • Performing face recognition with LBPH
      • Discarding results based on the confidence score
  • Swapping faces in the infrared
    • Modifying the application's loop
    • Masking a copy operation
  • Summary
• Chapter 6: Retrieving Images and Searching Using Image Descriptors
  • Technical requirements
  • Understanding types of feature detection and matching
    • Defining features
  • Detecting Harris corners
  • Detecting DoG features and extracting SIFT descriptors
    • Anatomy of a keypoint
  • Detecting Fast Hessian features and extracting SURF descriptors
  • Using ORB with FAST features and BRIEF descriptors
    • FAST
    • BRIEF
    • Brute-force matching
    • Matching a logo in two images
  • Filtering matches using K-Nearest Neighbors and the ratio test
  • Matching with FLANN
  • Performing homography with FLANN-based matches
  • A sample application – tattoo forensics
    • Saving image descriptors to file
    • Scanning for matches
  • Summary
• Chapter 7: Building Custom Object Detectors
  • Technical requirements
  • Understanding HOG descriptors
    • Visualizing HOG
    • Using HOG to describe regions of an image
  • Understanding NMS
  • Understanding SVMs
  • Detecting people with HOG descriptors
  • Creating and training an object detector
    • Understanding BoW
    • Applying BoW to computer vision
      • k-means clustering
  • Detecting cars
    • Combining an SVM with a sliding window
      • Detecting a car in a scene
      • Saving and loading a trained SVM
  • Summary
• Chapter 8: Tracking Objects
  • Technical requirements
  • Detecting moving objects with background subtraction
    • Implementing a basic background subtractor
    • Using a MOG background subtractor
    • Using a KNN background subtractor
    • Using GMG and other background subtractors
  • Tracking colorful objects using MeanShift and CamShift
    • Planning our MeanShift sample
    • Calculating and back-projecting color histograms
      • Understanding the parameters of cv2.calcHist
      • Understanding the parameters of cv2.calcBackProject
    • Implementing the MeanShift example
    • Using CamShift
  • Finding trends in motion using the Kalman filter
    • Understanding the predict and update phases
    • Tracking a mouse cursor
  • Tracking pedestrians
    • Planning the flow of the application
    • Comparing the object-oriented and functional paradigms
    • Implementing the Pedestrian class
    • Implementing the main function
    • Considering the next steps
  • Summary
• Chapter 9: Camera Models and Augmented Reality
  • Technical requirements
  • Understanding 3D image tracking and augmented reality
    • Understanding camera and lens parameters
    • Understanding cv2.solvePnPRansac
  • Implementing the demo application
    • Importing modules
    • Performing grayscale conversion
    • Performing 2D-to-3D spatial conversions
    • Implementing the application class
      • Initializing the tracker
      • Implementing the main loop
      • Tracking the image in 3D
      • Initializing and applying the Kalman filter
      • Drawing the tracking results and masking the tracked object
    • Running and testing the application
  • Improving the 3D tracking algorithm
  • Summary
• Chapter 10: Introduction to Neural Networks with OpenCV
  • Technical requirements
  • Understanding ANNs
    • Understanding neurons and perceptrons
    • Understanding the layers of a neural network
      • Choosing the size of the input layer
      • Choosing the size of the output layer
      • Choosing the size of the hidden layer
  • Training a basic ANN in OpenCV
  • Training an ANN classifier in multiple epochs
  • Recognizing handwritten digits with an ANN
    • Understanding the MNIST database of handwritten digits
    • Choosing training parameters for the MNIST database
    • Implementing a module to train the ANN
    • Implementing a minimal test module
    • Implementing the main module
    • Trying to improve the ANN's training
    • Finding other potential applications
  • Using DNNs from other frameworks in OpenCV
  • Detecting and classifying objects with third-party DNNs
  • Detecting and classifying faces with third-party DNNs
  • Summary
• Appendix A: Bending Color Space with the Curves Filter
• Other Book You May Enjoy
• Index