Book Image

Learning OpenCV 4 Computer Vision with Python 3 - Third Edition

By : Joseph Howse, Joe Minichino
Book Image

Learning OpenCV 4 Computer Vision with Python 3 - Third Edition

By: Joseph Howse, Joe Minichino

Overview of this book

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.

Related Content you might be interested in

Current Title:

Small book image
Learning OpenCV 4 Computer Vision with Python 3 - Third Edition
Joseph Howse | Joe Minichino
Feb, 2020 | 372 pages
Small book image
OpenCV 4 for Secret Agents.
Joseph Howse
Apr, 2019 | 336 pages
Small book image
OpenCV 3.x with Python By Example
Prateek Joshi | Gabriel Garrido Calvo
Jan, 2018 | 268 pages
Small book image
OpenCV 3 Computer Vision with Python Cookbook
Aleksandr Rybnikov | Aleksei Spizhevoi
Mar, 2018 | 306 pages
Table of Contents (13 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
1
Setting Up OpenCV
Setting Up OpenCV
Technical requirements
What's new in OpenCV 4
Choosing and using the right setup tools
Running samples
Finding documentation, help, and updates
Summary
Free Chapter
2
Handling Files, Cameras, and GUIs
Handling Files, Cameras, and GUIs
Technical requirements
Basic I/O scripts
Project Cameo (face tracking and image manipulation)
Cameo – an object-oriented design
Summary
3
Processing Images with OpenCV
Processing Images with OpenCV
Technical requirements
Converting images between different color models
Exploring the Fourier transform
Creating modules
Edge detection
Custom kernels – getting convoluted
Modifying the application
Edge detection with Canny
Contour detection
Detecting lines, circles, and other shapes
Summary
4
Depth Estimation and Segmentation
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
5
Detecting and Recognizing Faces
Detecting and Recognizing Faces
Technical requirements
Conceptualizing Haar cascades
Getting Haar cascade data
Using OpenCV to perform face detection
Swapping faces in the infrared
Summary
6
Retrieving Images and Searching Using Image Descriptors
Retrieving Images and Searching Using Image Descriptors
Technical requirements
Understanding types of feature detection and matching
Detecting Harris corners
Detecting DoG features and extracting SIFT descriptors
Detecting Fast Hessian features and extracting SURF descriptors
Using ORB with FAST features and BRIEF descriptors
Filtering matches using K-Nearest Neighbors and the ratio test
Matching with FLANN
Performing homography with FLANN-based matches
A sample application – tattoo forensics
Summary
7
Building Custom Object Detectors
Building Custom Object Detectors
Technical requirements
Understanding HOG descriptors
Understanding NMS
Understanding SVMs
Detecting people with HOG descriptors
Creating and training an object detector
Detecting cars
Summary
8
Tracking Objects
Tracking Objects
Technical requirements
Detecting moving objects with background subtraction
Tracking colorful objects using MeanShift and CamShift
Finding trends in motion using the Kalman filter
Tracking pedestrians
Summary
9
Camera Models and Augmented Reality
Camera Models and Augmented Reality
Technical requirements
Understanding 3D image tracking and augmented reality
Implementing the demo application
Improving the 3D tracking algorithm
Summary
10
Introduction to Neural Networks with OpenCV
Introduction to Neural Networks with OpenCV
Technical requirements
Understanding ANNs
Training a basic ANN in OpenCV
Training an ANN classifier in multiple epochs
Recognizing handwritten digits with an ANN
Using DNNs from other frameworks in OpenCV
Detecting and classifying objects with third-party DNNs
Detecting and classifying faces with third-party DNNs
Summary
11
Other Book You May Enjoy
Other Book You May Enjoy
Leave a review - let other readers know what you think
Appendix A: Bending Color Space with the Curves Filter
Appendix A: Bending Color Space with the Curves Filter
Formulating a curve
Caching and applying a curve
Designing object-oriented curve filters
Emulating photo films
Summary

Capturing frames from a depth camera

Back in Chapter 2, Handling Files, Cameras, and GUIs, we discussed the concept that a computer can have multiple video capture devices and each device can have multiple channels. Suppose a given device is a depth camera. Each channel might correspond to a different lens and sensor. Also, each channel might correspond to different kinds of data, such as a normal color image versus a depth map. OpenCV, via its optional support for OpenNI 2, allows us to request any of the following channels from a depth camera (though a given camera might support only some of these channels):

  • cv2.CAP_OPENNI_DEPTH_MAP: This is a depth map—a grayscale image in which each pixel value is the estimated distance from the camera to a surface. Specifically, each pixel value is a 16-bit unsigned integer representing a depth measurement in millimeters.
  • cv2.CAP_OPENNI_POINT_CLOUD_MAP...
Previous Section
End of Section 4
Next Section