Updated for OpenCV 4 and Python 3, this book covers the latest on depth cameras, 3D tracking, augmented reality, and deep neural networks, helping you solve real-world computer vision problems with practical code
Key Features
• Build powerful computer vision applications in concise code with OpenCV 4 and Python 3
• Learn the fundamental concepts of image processing, object classification, and 2D and 3D tracking
• Train, use, and understand machine learning models such as Support Vector Machines (SVMs) and neural networks
Book Description
Computer vision is a rapidly evolving science, encompassing diverse applications and techniques. This book will not only help those who are getting started with computer vision but also experts in the domain. You'll be able to put theory into practice by building apps with OpenCV 4 and Python 3.
You'll start by understanding OpenCV 4 and how to set it up with Python 3 on various platforms. Next, you'll learn how to perform basic operations such as reading, writing, manipulating, and displaying still images, videos, and camera feeds. From taking you through image processing, video analysis, and depth estimation and segmentation, to helping you gain practice by building a GUI app, this book ensures you'll have opportunities for hands-on activities. Next, you'll tackle two popular challenges: face detection and face recognition. You'll also learn about object classification and machine learning concepts, which will enable you to create and use object detectors and classifiers, and even track objects in movies or video camera feed. Later, you'll develop your skills in 3D tracking and augmented reality. Finally, you'll cover ANNs and DNNs, learning how to develop apps for recognizing handwritten digits and classifying a person's gender and age.
By the end of this book, you'll have the skills you need to execute real-world computer vision projects.
What you will learn
• Install and familiarize yourself with OpenCV 4's Python 3 bindings
• Understand image processing and video analysis basics
• Use a depth camera to distinguish foreground and background regions
• Detect and identify objects, and track their motion in videos
• Train and use your own models to match images and classify objects
• Detect and recognize faces, and classify their gender and age
• Build an augmented reality application to track an image in 3D
• Work with machine learning models, including SVMs, artificial neural networks (ANNs), and deep neural networks (DNNs)
Who this book is for
If you are interested in learning computer vision, machine learning, and OpenCV in the context of practical real-world applications, then this book is for you. This OpenCV book will also be useful for anyone getting started with computer vision as well as experts who want to stay up-to-date with OpenCV 4 and Python 3. Although no prior knowledge of image processing, computer vision or machine learning is required, familiarity with basic Python programming is a must.
Author(s): Joseph Howse, Joe Minichino
Edition: 3
Publisher: Packt Publishing
Year: 2020
Language: English
Commentary: True PDF
Pages: 372
City: Birmingham, UK
Tags: Neural Networks; Computer Vision; Image Processing; OpenCV; Python; Face Recognition; Kalman Filtering; Augmented Reality; Fourier Transform; Image Segmentation; Object Detection
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
