Chapter 1, A Taste of Machine Learning, starts us off with installing the required software and Python modules for this book.

Chapter 2, Working with Data in OpenCV, takes a look at some basic OpenCV functions.

Chapter 3, First Steps in Supervised Learning, will cover the basics of supervised learning methods in machine learning. We will have a look at some examples of supervised learning methods using OpenCV and the scikit-learn library in Python.

Chapter 4, Representing Data and Engineering Features, will cover concepts such as feature detection and feature recognition using ORB in OpenCV. We will also try to understand important concepts such as the curse of dimensionality.

Chapter 5, Using Decision Trees to Make a Medical Diagnosis, will introduce decision trees and important concepts related to them, including the depth of trees and techniques such as pruning. We will also cover a practical application of predicting breast cancer diagnoses using decision trees.

Chapter 6, Detecting Pedestrians with Support Vector Machines, will start off with an introduction to support vector machines and how they can be implemented in OpenCV. We will also cover an application of pedestrian detection using OpenCV.

Chapter 7, Implementing a Spam Filter with Bayesian Learning, will discuss techniques such as the Naive Bayes algorithm, multinomial Naive Bayes, and more, as well as how they can be implemented. Finally, we will build a machine learning application to classify data into spam and ham.

Chapter 8, Discovering Hidden Structures with Unsupverised Learning, will be our first introduction to the second class of machine learning algorithms—unsupervised learning. We will discuss techniques such as clustering using k-nearest neighbors, k-means, and more.

Chapter 9, Using Deep Learning to Classify Handwritten Digits, will introduce deep learning techniques and we will see how we can use deep neural networks to classify images from the MNIST dataset.

Chapter 10, Ensemble Methods for Classification, will cover topics such as random forest, bagging, and boosting for classification purposes.

Chapter 11, Selecting the Right Model with Hyperparameter Tuning, will go over the process of selecting the optimum set of parameters in various machine learning methods in order to improve the performance of a model.

Chapter 12, Using OpenVINO with OpenCV, will introduce OpenVINO Toolkit, which was introduced in OpenCV 4.0. We will also go over how we can use it in OpenCV using image classification as an example.

Chapter 13, Conclusion, will provide a summary of the major topics that we have covered in the book and talk about what you can do next.