Book Image

Computer Vision Projects with OpenCV and Python 3

By : Matthew Rever
Book Image

Computer Vision Projects with OpenCV and Python 3

By: Matthew Rever

Overview of this book

Python is the ideal programming language for rapidly prototyping and developing production-grade codes for image processing and Computer Vision with its robust syntax and wealth of powerful libraries. This book will help you design and develop production-grade Computer Vision projects tackling real-world problems. With the help of this book, you will learn how to set up Anaconda and Python for the major OSes with cutting-edge third-party libraries for Computer Vision. You'll learn state-of-the-art techniques for classifying images, finding and identifying human postures, and detecting faces within videos. You will use powerful machine learning tools such as OpenCV, Dlib, and TensorFlow to build exciting projects such as classifying handwritten digits, detecting facial features,and much more. The book also covers some advanced projects, such as reading text from license plates from real-world images using Google’s Tesseract software, and tracking human body poses using DeeperCut within TensorFlow. By the end of this book, you will have the expertise required to build your own Computer Vision projects using Python and its associated libraries.
Table of Contents (9 chapters)

Acquiring and processing MNIST digit data

As mentioned, we will be covering handwritten digit recognition with scikit-learn and TensorFlow. Here, we're going to learn how machine learning can be applied to computer vision projects, and we're going to learn a couple of different ways and models, using a couple of different Python modules. Let's get started.

You have probably heard about machine learning. Here, we will be particularly talking about supervised machine learning, where we have a bunch of examples that we want to accomplish. So, rather than explicitly telling the computer what we want, we give an example.

Let's take the case of the handwritten digits 0 through 9, which have labels that are created by humans indicating what those digits are supposed to be. So, rather than hand-coding features and explicitly telling the computer what the algorithm...