Preface

As the world changes and humans build smarter and better machines, the demand for machine learning and computer vision experts increases. Machine learning, as the name suggests, is the process of a machine learning to make predictions given a certain set of parameters as input. Computer vision, on the other hand, gives a machine vision; that is, it makes the machine aware of visual information. When you combine these technologies, you get a machine that can use visual data to make predictions, which brings machines one step closer to having human capabilities. When you add deep learning to it, the machine can even surpass human capabilities in terms of making predictions. This might seem far-fetched, but with AI systems taking over decision-based systems, this has actually become a reality. You have AI cameras, AI monitors, AI sound systems, AI-powered processors, and more. We cannot promise you that you will be able to build an AI camera after reading this book, but we do intend to provide you with the tools necessary for you to do so. The most powerful tool that we are going to introduce is the OpenCV library, which is the world's largest computer vision library. Even though its use in machine learning is not very common, we have provided some examples and concepts on how it can be used for machine learning. We have gone with a hands-on approach in this book and we recommend that you try out every single piece of code present in this book to build an application that showcases your knowledge. The world is changing and this book is our way of helping young minds change it for the better.