Machine Learning for OpenCV 4

By : Sharma, Michael Beyeler (USD), Vishwesh Ravi Shrimali , Michael Beyeler

Buy this Book

Machine Learning for OpenCV 4

By: Sharma, Michael Beyeler (USD), Vishwesh Ravi Shrimali , Michael Beyeler

Buy this Book

Overview of this book

OpenCV is an opensource library for building computer vision apps. The latest release, OpenCV 4, offers a plethora of features and platform improvements that are covered comprehensively in this up-to-date second edition. You'll start by understanding the new features and setting up OpenCV 4 to build your computer vision applications. You will explore the fundamentals of machine learning and even learn to design different algorithms that can be used for image processing. Gradually, the book will take you through supervised and unsupervised machine learning. You will gain hands-on experience using scikit-learn in Python for a variety of machine learning applications. Later chapters will focus on different machine learning algorithms, such as a decision tree, support vector machines (SVM), and Bayesian learning, and how they can be used for object detection computer vision operations. You will then delve into deep learning and ensemble learning, and discover their real-world applications, such as handwritten digit classification and gesture recognition. Finally, you’ll get to grips with the latest Intel OpenVINO for building an image processing system. By the end of this book, you will have developed the skills you need to use machine learning for building intelligent computer vision applications with OpenCV 4.

Preface

Who this book is for

What this book covers

To get the most out of this book

Get in touch

Free Chapter

Section 1: Fundamentals of Machine Learning and OpenCV

A Taste of Machine Learning

Technical requirements

Getting started with machine learning

Problems that machine learning can solve

Getting started with Python

Getting started with OpenCV

Installation

Applications of machine learning

What's new in OpenCV 4.0?

Summary

Working with Data in OpenCV

Technical requirements

Understanding the machine learning workflow

Dealing with data using OpenCV and Python

Summary

First Steps in Supervised Learning

Technical requirements

Understanding supervised learning

Using classification models to predict class labels

Using regression models to predict continuous outcomes

Classifying iris species using logistic regression

Summary

Representing Data and Engineering Features

Technical requirements

Understanding feature engineering

Preprocessing data

Understanding dimensionality reduction

Representing categorical variables

Representing text features

Representing images

Summary

Section 2: Operations with OpenCV

Using Decision Trees to Make a Medical Diagnosis

Technical requirements

Understanding decision trees

Using decision trees to diagnose breast cancer

Using decision trees for regression

Summary

Detecting Pedestrians with Support Vector Machines

Technical requirement

Understanding linear SVMs

Dealing with nonlinear decision boundaries

Detecting pedestrians in the wild

Summary

Implementing a Spam Filter with Bayesian Learning

Technical requirements

Understanding Bayesian inference

Implementing your first Bayesian classifier

Classifying emails using the Naive Bayes classifier

Summary

Discovering Hidden Structures with Unsupervised Learning

Technical requirements

Understanding unsupervised learning

Understanding k-means clustering

Understanding expectation-maximization

Compressing color spaces using k-means

Classifying handwritten digits using k-means

Organizing clusters as a hierarchical tree

Summary

Section 3: Advanced Machine Learning with OpenCV

Using Deep Learning to Classify Handwritten Digits

Technical requirements

Understanding the McCulloch-Pitts neuron

Understanding the perceptron

Implementing your first perceptron

Understanding multilayer perceptrons

Getting acquainted with deep learning

Classifying handwritten digits

Summary

Ensemble Methods for Classification

Technical requirements

Understanding ensemble methods

Combining decision trees into a random forest

Using random forests for face recognition

Implementing AdaBoost

Combining different models into a voting classifier

Summary

Selecting the Right Model with Hyperparameter Tuning

Technical requirements

Evaluating a model

Understanding cross-validation

Estimating robustness using bootstrapping

Assessing the significance of our results

Tuning hyperparameters with grid search

Scoring models using different evaluation metrics

Chaining algorithms together to form a pipeline

Summary

Using OpenVINO with OpenCV

Technical requirements

Introduction to OpenVINO

OpenVINO toolkit installation

Interactive face detection demo

Using OpenVINO Inference Engine with OpenCV

Using OpenVINO Model Zoo with OpenCV

Image classification using OpenCV with OpenVINO Inference Engine

Summary

Conclusion

Technical requirements

Approaching a machine learning problem

Building your own estimator

Where to go from here

Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

5 star

4 star

3 star

2 star

1 star

Compressing color spaces using k-means

One interesting use case of k-means is the compression of image color spaces. For example, a standard color image comes with 24-bit color depth, providing for a total of 16,777,216 color varieties. However, in most images, a large number of colors will be unused, and many of the pixels in the image will have similar values. The compressed image can then be sent over the internet at a faster speed, and at the receiver end, it can be decompressed to get back the original image. Hence, reducing the storage and transmission cost. However, the image color space compression will be lossy and you might not notice fine details in the image after compression.

Alternatively, we can use k-means to reduce the color palette too. The idea here is to think of the cluster centers as the decreased color palette. Then, k-means will organize the millions of...