Building Computer Vision Projects With OpenCV 4 and C++ by Escrivá, David Millán -- Read -- Imperial Library of Trantor

Index

Title Page Copyright and Credits

Building Computer Vision Projects with OpenCV 4 and C++

About Packt

Why subscribe? Packt.com

Contributors

About the authors Packt is searching for authors like you

Preface

Who this book is for What this book covers To get the most out of this book

Download the example code files Conventions used

Get in touch

Reviews

Getting Started with OpenCV

Understanding the human visual system How do humans understand image content?

Why is it difficult for machines to understand image content?

What can you do with OpenCV?

Inbuilt data structures and input/output Image processing operations GUI Video analysis 3D reconstruction Feature extraction Object detection Machine learning Computational photography Shape analysis Optical flow algorithms Face and object recognition Surface matching Text detection and recognition Deep learning

Installing OpenCV

Windows Mac OS X Linux

Summary

An Introduction to the Basics of OpenCV

Technical requirements Basic CMake configuration file Creating a library Managing dependencies Making the script more complex Images and matrices Reading/writing images Reading videos and cameras Other basic object types

Vec object type Scalar object type Point object type Size object type Rect object type RotatedRect object type

Basic matrix operations Basic data persistence and storage

Writing to FileStorage

Summary

Learning Graphical User Interfaces

Technical requirements Introducing the OpenCV user interface Basic graphical user interface with OpenCV

Adding slider and mouse events to our interfaces

Graphic user interface with Qt

Adding buttons to the user interface

OpenGL support Summary

Delving into Histogram and Filters

Technical requirements Generating a CMake script file Creating the graphical user interface Drawing a histogram Image color equalization Lomography effect Cartoonize effect Summary

Automated Optical Inspection, Object Segmentation, and Detection

Technical requirements Isolating objects in a scene Creating an application for AOI Preprocessing the input image

Noise removal Removing the background using the light pattern for segmentation Thresholding

Segmenting our input image

The connected components algorithm The findContours algorithm

Summary

Learning Object Classification

Technical requirements Introducing machine learning concepts

OpenCV machine learning algorithms

Computer vision and the machine learning workflow Automatic object inspection classification example

Feature extraction Training an SVM model Input image prediction

Summary

Detecting Face Parts and Overlaying Masks

Technical requirements Understanding Haar cascades What are integral images? Overlaying a face mask in a live video

What happened in the code?

Get your sunglasses on

Looking inside the code

Tracking the nose, mouth, and ears Summary

Video Surveillance, Background Modeling, and Morphological Operations

Technical requirements Understanding background subtraction Naive background subtraction

Does it work well?

Frame differencing

How well does it work?

The Mixture of Gaussians approach

What happened in the code?

Morphological image processing

What's the underlying principle?

Slimming the shapes Thickening the shapes Other morphological operators

Morphological opening Morphological closing Drawing the boundary Top Hat transform Black Hat transform

Summary

Learning Object Tracking

Technical requirements Tracking objects of a specific color Building an interactive object tracker Detecting points using the Harris corner detector Good features to track Feature-based tracking

Lucas-Kanade method Farneback algorithm

Summary

Developing Segmentation Algorithms for Text Recognition

Technical requirements Introducing optical character recognition Preprocessing stage

Thresholding the image Text segmentation

Creating connected areas Identifying paragraph blocks Text extraction and skewing adjustment

Installing Tesseract OCR on your operating system

Installing Tesseract on Windows

Building the latest library Setting up Tesseract in Visual Studio

Static linking

Installing Tesseract on Mac

Using the Tesseract OCR library

Creating an OCR function

Sending the output to a file

Summary

Text Recognition with Tesseract

Technical requirements How the text API works

The scene detection problem Extremal regions Extremal region filtering

Using the text API

Text detection Text extraction Text recognition

Summary

Deep Learning with OpenCV

Technical requirements Introduction to deep learning

What is a neural network and how can we learn from data? Convolutional neural networks

Deep learning in OpenCV YOLO – real-time object detection

YOLO v3 deep learning model architecture The YOLO dataset, vocabulary, and model Importing YOLO into OpenCV

Face detection with SSD

SSD model architecture Importing SSD face detection into OpenCV

Summary

Cartoonifier and Skin Color Analysis on the RaspberryPi

Accessing the webcam Main camera processing loop for a desktop app

Generating a black and white sketch Generating a color painting and a cartoon Generating an evil mode using edge filters Generating an alien mode using skin detection

Skin detection algorithm Showing the user where to put their face

Implementation of the skin color changer

Reducing the random pepper noise from the sketch image

Porting from desktop to an embedded device

Equipment setup to develop code for an embedded device

Configuring a new Raspberry Pi

Installing OpenCV on an embedded device

Using the Raspberry Pi Camera Module

Installing the Raspberry Pi Camera Module driver

Making Cartoonifier run in fullscreen Hiding the mouse cursor Running Cartoonifier automatically after bootup Speed comparison of Cartoonifier on desktop versus embedded

Changing the camera and camera resolution

Power draw of Cartoonifier running on desktop versus embedded system

Streaming video from Raspberry Pi to a powerful computer

Customizing your embedded system!

Summary

Explore Structure from Motion with the SfM Module

Technical requirements Core concepts of SfM

Calibrated cameras and epipolar geometry Stereo reconstruction and SfM

Implementing SfM in OpenCV

Image feature matching Finding feature tracks 3D reconstruction and visualization MVS for dense reconstruction

Summary

Face Landmark and Pose with the Face Module

Technical requirements Theory and context

Active appearance models and constrained local models Regression methods

Facial landmark detection in OpenCV

Measuring error

Estimating face direction from landmarks

Estimated pose calculation Projecting the pose on the image

Summary

Number Plate Recognition with Deep Convolutional Networks

Introduction to ANPR ANPR algorithm Plate detection

Segmentation Classification

Plate recognition

OCR segmentation Character classification using a convolutional neural network

Creating and training a convolutional neural network with TensorFlow

Preparing the data Creating a TensorFlow model Preparing a model for OpenCV Import and use model in OpenCV C++ code

Summary

Face Detection and Recognition with the DNN Module

Introduction to face detection and face recognition

Face detection

Implementing face detection using OpenCV cascade classifiers

Loading a Haar or LBP detector for object or face detection Accessing the webcam Detecting an object using the Haar or LBP classifier Detecting the face

Implementing face detection using the OpenCV deep learning module

Face preprocessing

Eye detection Eye search regions

Geometrical transformation Separate histogram equalization for left and right sides Smoothing Elliptical mask

Collecting faces and learning from them

Collecting preprocessed faces for training Training the face recognition system from collected faces Viewing the learned knowledge Average face Eigenvalues, Eigenfaces, and Fisherfaces

Face recognition

Face identification – recognizing people from their faces Face verification—validating that it is the claimed person

Finishing touches—saving and loading files Finishing touches—making a nice and interactive GUI

Drawing the GUI elements

Startup mode Detection mode Collection mode Training mode Recognition mode

Checking and handling mouse clicks

Summary References

Android Camera Calibration and AR Using the ArUco Module

Technical requirements Augmented reality and pose estimation

Camera calibration Augmented reality markers for planar reconstruction

Camera access in Android OS

Finding and opening the camera

Camera calibration with ArUco Augmented reality with jMonkeyEngine Summary

iOS Panoramas with the Stitching Module

Technical requirements Panoramic image stitching methods

Feature extraction and robust matching for panoramas

Affine constraint Random sample consensus (RANSAC) Homography constraint Bundle Adjustment

Warping images for panorama creation

Project overview Setting up an iOS OpenCV project with CocoaPods iOS UI for panorama capture OpenCV stitching in an Objective-C++ wrapper Summary Further reading

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 Summary

Avoiding Common Pitfalls in OpenCV

History of OpenCV from v1 to v4

OpenCV and the data revolution in computer vision

Historic algorithms in OpenCV

How to check when an algorithm was added to OpenCV

Common pitfalls and suggested solutions Summary Further reading

Other Books You May Enjoy

Leave a review - let other readers know what you think

← Prev
Back
Next →

← Prev
Back
Next →