MACHINE LEARNING FOR OPENCV 4 : intelligent algorithms for building image processing apps

MACHINE LEARNING FOR OPENCV 4  intelligent algorithms for building image processing apps

MACHINE LEARNING FOR OPENCV 4 : intelligent algorithms for building image processing apps
MACHINE LEARNING FOR OPENCV 4 : intelligent algorithms for building image processing apps

MACHINE LEARNING FOR OPENCV 4 : intelligent algorithms for building image processing apps... using opencv 4, python, and scikit-learn, 2nd edit.

ISBN: 9781789536300,1789536308


As the world changes and humans build smarter and better machines, the demand for them is
Computer learning and computer vision experts are growing. Machine learning, as a name
It is suggested, it is the process of machine learning to make predictions given a particular set of
Parameters as input. 

Computer vision, on the other hand, gives machine vision; This is Keeps the device aware of the visual information. When you incorporate these technologies, You get a machine that can use visual data to make predictions, which makes machines one Get close to possessing human capabilities. When you add deep learning to it, the device Human capabilities can even be exceeded in predictions.

 This may seem out of reach, but with artificial intelligence systems taking on decision-based systems, this is becoming a reality reality. 
You have AI cameras, AI screens, AI sound systems, AI processors, and More.
 We cannot promise that you will be able to build an AI camera after reading this But we intend to provide you with the necessary tools to do so.
 More The powerful tool we'll be introducing is the OpenCV library, which is the world
The largest computer vision library. Although its use in machine learning is not difficult
In general, we have provided some examples and concepts on how to use it Machine learning. We went with a pragmatic approach in this book and we We recommend trying each part of the code in this book to build An application that displays your knowledge. The world is changing and this book is our book A way to help young minds change it for the better.
for whom is this book We tried to explain all concepts from scratch to make the book fit
Beginners as well as advanced readers. We recommend that readers have some basics
Knowledge of Python programming, but not mandatory. Whenever you encounter some
Python formula that you can't understand, be sure to search for it in Internet. Help is always offered to those looking for it.

What this book covers

The first chapter "Tasting Machine Learning" begins with installing the required software
And Python units for this book.

Chapter 2, Working with Data in OpenCV, looks at some of the core OpenCV functions.
an introduction
Chapter 3, first steps in supervised learning, will cover the basics of supervised learning
Methods in machine learning. We'll look at some examples of supervised learning Methods using the OpenCV and scikit-learning library in Python.

Chapter 4, which represents data and engineering features, will cover concepts such as feature
Detection and recognition of features using ORB in OpenCV. We will also try to understand
Important concepts like dimensional curse.

Chapter 5, using decision trees to make a medical diagnosis, will introduce decision trees
Important concepts related to it, including tree depth and techniques such as pruning. 
We'll also cover the practical application of breast cancer diagnostic prediction Using decision trees.

Chapter 6, Pedestrian Detection Using Vector Supporting Machines, will begin with a sign
An introduction to vector vector support and how to implement it in OpenCV.
We'll also be covering the pedestrian detection app with OpenCV.

Chapter 7, implementing a spam filter with Bayesian learning, will discuss techniques such as
The Naive Bayes algorithm, the Naive Bayes polynomial, and more, as well as how they might be executed.
 Finally, we will create a machine learning application to classify data into
Spam and ham.

Chapter 8, Discovering Hidden Structures with Unexplained Learning, will be the first
Introduction to the second category of machine learning algorithms - learning without supervision.
We will discuss techniques such as grouping using k-closest neighbors, k means, and More.

Chapter 9, using deep learning to classify handwritten numbers, will introduce deep learning
Techniques and we'll see how we can use deep neural networks to categorize images from
MNIST dataset.

Chapter 10 will cover classification methods, topics such as random forest,
Packaging and reinforcement for classification purposes.

Chapter 11, selecting the correct model with Hyperparameter settings, will review the process
Choose the optimal set of parameters in the various machine learning methods for Improve the performance of the model.

Chapter 12, using OpenVINO with OpenCV, will introduce the OpenVINO toolkit, which was
Introduced in OpenCV 4.0. We'll also go over how we can use it in OpenCV using the image
Classification as an example.

Chapter 13, Conclusion, will provide a summary of the main topics we have covered
In the book, talk about what you can do next.

Publier un commentaire

0 Commentaires