Book Image

Mastering OpenCV 4 - Third Edition

By : Roy Shilkrot, David Millán Escrivá

Book Image

Mastering OpenCV 4 - Third Edition

By: Roy Shilkrot, David Millán Escrivá

Overview of this book

Mastering OpenCV, now in its third edition, targets computer vision engineers taking their first steps toward mastering OpenCV. Keeping the mathematical formulations to a solid but bare minimum, the book delivers complete projects from ideation to running code, targeting current hot topics in computer vision such as face recognition, landmark detection and pose estimation, and number recognition with deep convolutional networks. You’ll learn from experienced OpenCV experts how to implement computer vision products and projects both in academia and industry in a comfortable package. You’ll get acquainted with API functionality and gain insights into design choices in a complete computer vision project. You’ll also go beyond the basics of computer vision to implement solutions for complex image processing projects. By the end of the book, you will have created various working prototypes with the help of projects in the book and be well versed with the new features of OpenCV4.

Preface

Who this book is for

What this book covers

To get the most out of this book

Free Chapter

Cartoonifier and Skin Color Analysis on the RaspberryPi

Cartoonifier and Skin Color Analysis on the RaspberryPi

Accessing the webcam

Main camera processing loop for a desktop app

Implementation of the skin color changer

Porting from desktop to an embedded device

Explore Structure from Motion with the SfM Module

Explore Structure from Motion with the SfM Module

Technical requirements

Core concepts of SfM

Implementing SfM in OpenCV

Face Landmark and Pose with the Face Module

Face Landmark and Pose with the Face Module

Technical requirements

Theory and context

Facial landmark detection in OpenCV

Estimating face direction from landmarks

Number Plate Recognition with Deep Convolutional Networks

Number Plate Recognition with Deep Convolutional Networks

Introduction to ANPR

Plate detection

Plate recognition

Face Detection and Recognition with the DNN Module

Face Detection and Recognition with the DNN Module

Introduction to face detection and face recognition

Introduction to Web Computer Vision with OpenCV.js

Introduction to Web Computer Vision with OpenCV.js

What is OpenCV.js?

Compile OpenCV.js

Basic introduction to OpenCV.js development

Accessing webcam streams

Image processing and basic user interface

Optical flow in your browser

Face detection using a Haar cascade classifier in your browser

Android Camera Calibration and AR Using the ArUco Module

Android Camera Calibration and AR Using the ArUco Module

Technical requirements

Augmented reality and pose estimation

Camera access in Android OS

Camera calibration with ArUco

Augmented reality with jMonkeyEngine

iOS Panoramas with the Stitching Module

iOS Panoramas with the Stitching Module

Technical requirements

Panoramic image stitching methods

Project overview

Setting up an iOS OpenCV project with CocoaPods

iOS UI for panorama capture

OpenCV stitching in an Objective-C++ wrapper

Further reading

Finding the Best OpenCV Algorithm for the Job

Finding the Best OpenCV Algorithm for the Job

Technical requirements

Is it covered in OpenCV?

Algorithm options in OpenCV

Which algorithm is best?

Example comparative performance test of algorithms

Avoiding Common Pitfalls in OpenCV

Avoiding Common Pitfalls in OpenCV

History of OpenCV from v1 to v4

Historic algorithms in OpenCV

Common pitfalls and suggested solutions

Further reading

Other Books You May Enjoy

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

5 star

0

4 star

0

3 star

0

2 star

0

1 star

0

Technical requirements

The technologies and softwares used in this chapter are the following:

OpenCV v3 or v4 Android SDK compiled with the ArUco contrib module: https://github.com/Mainvooid/opencv-android-sdk-with-contrib
Android Studio v3.2+
Android device running Android OS v6.0+

Build instructions for these components, as well as the code to implement the concepts presented in this chapter, will be provided in the accompanying code repository.

To run the examples, a printed calibration board is required. The board image can be generated programmatically with the ArUco cv::aruco::CharucoBoard::draw function, and can then be printed using a home printer. The board works best if it is glued to a hard surface, such as a cardboard or plastic sheet. After printing the board, precise measurements of the board marker's size should be taken (with a ruler or caliper), to make...