You can refer to the code for this chapter at the following link: https://github.com/PacktPublishing/Machine-Learning-for-OpenCV-Second-Edition/tree/master/Chapter01.

Here is a short summary of the software and hardware requirements:

• OpenCV version 4.1.x (4.1.0 or 4.1.1 will both work just fine).
• Python version 3.6 (any Python version 3.x will be fine).
• Anaconda Python 3 for installing Python and the required modules.
• You can use any OS—macOS, Windows, and Linux-based OS—with this book. We recommend you have at least 4 GB RAM in your system.
• You don't need to have a GPU to run the code provided with this book.

Machine learning has been around for at least 60 years. Growing out of the quest for artificial intelligence, early machine learning systems inferred the hand-coded rules of if...else statements to process data and make decisions. Think of a spam filter whose job is to parse incoming emails and move unwanted messages to a spam folder as shown here in the following diagram:

We could come up with a blacklist of words that, whenever they show up in a message, would mark an email as spam. This is a simple example of a hand-coded expert system. (We will build a smarter one in Chapter 7, Implementing a Spam Filter with Bayesian Learning.)

These expert decision rules can become arbitrarily complicated if we are allowed to combine and nest them in what is known as a decision tree (Chapter 5, Using Decision Trees to Make a Medical Diagnosis). Then...

Most machine learning problems belong to one of the following three main categories:

• In supervised learning, we have what is referred to as the label for a data point. Now, this can be the class of an object that is captured in the image, a bounding box around a face, the digit present in the image, or anything else. Think of it as a teacher who teaches but also tells you what the correct answer is to a problem. Now, the student can try to devise a model or an equation that takes into account all the problems and their correct answers and finds out the answer to a problem that does (or does not) have a correct answer. The data that goes into learning the model is called the training data and the data on which the process/model is tested is called test data. These predictions come in two flavors, such as identifying new photos with the...

Python has become the common language for many data science and machine learning applications, thanks to its great number of open source libraries for processes such as data loading, data visualization, statistics, image processing, and natural language processing. One of the main advantages of using Python is the ability to interact directly with the code, using a Terminal or other tools such as the Jupyter Notebook, which we'll look at shortly.

If you have mostly been using OpenCV in combination with C++, I would strongly suggest that you switch to Python, at least for the purpose of studying this book. This decision has not been made out of spite! Quite the contrary: I have done my fair share of C/C++ programming—especially in combination with GPU computing via NVIDIA's Compute Unified Device Architecture (CUDA)—and I like...

Being the avid user of OpenCV that I believe you are, I probably don't have to convince you about the power of OpenCV.

Built to provide a common infrastructure for computer vision applications, OpenCV has become a comprehensive set of both classic and state-of-the-art computer vision and machine learning algorithms. According to their own documentation, OpenCV has a user community of more than 47,000 people and has been downloaded over seven million times. That's pretty impressive! As an open source project, it is very easy for researchers, businesses, and government bodies to utilize and modify already available code.

That being said, a number of open source machine learning libraries have popped up as part of the recent machine learning boom that provide far more functionality than OpenCV. A prominent example is scikit-learn, which provides...

Before we get started, let's make sure that we have all the tools and libraries installed that are necessary to create a fully functioning data science environment. After downloading the latest code for this book from GitHub, we are going to install the following software:

• Python's Anaconda distribution, based on Python 3.6 or higher
• OpenCV 4.1
• Some supporting packages

Machine learning, artificial intelligence, deep learning, and data science are four terms that I believe are going to change the way we have always looked at things. Let's see if I can convince you why I believe so.

From making a computer learn how to play Go and defeat the world champion of the very same game to using the same branch to detect whether a person has a tumor or not just by seeing their brain's CT Scan, machine learning has left its mark in every single domain. One of the projects that I worked on was using machine learning to determine the residual life cycle of boiler water wall tubes in thermal power plants. The proposed solution was successful in saving a huge amount of money by using the tubes more efficiently. If you thought that machine learning applications are limited to engineering and medical science, then you...

So, we come to the last section of the very first chapter. I will keep it short and to the point since you as a reader can safely skip it. The topic of our discussion is OpenCV 4.0.

OpenCV 4.0 is a result of three and a half years of hard work and bug fixes by OpenCV and was finally released in November 2018. In this section, we will look at some of the major changes and new features in OpenCV 4.0:

• With the OpenCV 4.0 release, OpenCV has officially become a C++11 library. This means that you have to make sure that a C++11 compliant compiler is present in your system when you are trying to compile OpenCV 4.0.
• In continuation of the previous point, a lot of C APIs have been removed. Some of the modules that have been affected include Video IO module (videoio), Object Detection module (objdetect), and others. File IO for XML, YAML, and JSON have also...

In this chapter, we talked about machine learning at a high abstraction level: what it is, why it is important, and what kinds of problems it can solve. We learned that machine learning problems come in three flavors: supervised learning, unsupervised learning, and reinforcement learning. We talked about the prominence of supervised learning, and that this field can be further divided into two subfields: classification and regression. Classification models allow us to categorize objects into known classes (such as animals into cats and dogs), whereas regression analysis can be used to predict continuous outcomes of target variables (such as the sales price of used cars).

We also learned how to set up a data science environment using the Python Anaconda distribution, how to get the latest code of this book from GitHub, and how to run code in a Jupyter Notebook.

With these...