Computer Vision Projects with OpenCV and Python 3

图书信息

作者	Matthew Rever
出版社	Packt Publishing
ISBN	9781789954906
出版时间	2018-12-28
字数	18.1万
分类	进口书,外文原版书,电脑,网络

读书简介

Gain a working knowledge of advanced machine learning and explore Python’s powerful tools for extracting data from images and videos Key Features *Implement image classification and object detection using machine learning and deep learning *Perform image classification, object detection, image segmentation, and other Computer Vision tasks *Crisp content with a practical approach to solving real-world problems in Computer Vision Book Description 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. What you will learn *Install and run major Computer Vision packages within Python *Apply powerful support vector machines for simple digit classification *Understand deep learning with TensorFlow *Build a deep learning classifier for general images *Use LSTMs for automated image captioning *Read text from real-world images *Extract human pose data from images Who this book is for Python programmers and machine learning developers who wish to build exciting Computer Vision projects using the power of machine learning and OpenCV will find this book useful. The only prerequisite for this book is that you should have a sound knowledge of Python programming.

目录

Title Page

Copyright and Credits

Computer Vision Projects with OpenCV and Python 3

About Packt

Why subscribe?

Packt.com

Contributors

About the author

Packt is searching for authors like you

Preface

Who this book is for

What this book covers

To get the most out of this book

Download the example code files

Download the color images

Conventions used

Get in touch

Reviews

Setting Up an Anaconda Environment

Introducing and installing Python and Anaconda

Installing Anaconda

Installing additional libraries

Installing OpenCV

Installing dlib

Installing Tesseract

Installing TensorFlow

Exploring Jupyter Notebook

Summary

Image Captioning with TensorFlow

Technical requirements

Introduction to image captioning

Difference between image classification and image captioning

Recurrent neural networks with long short-term memory

Google Brain im2txt captioning model

Running the captioning code on Jupyter

Analyzing the result captions

Running the captioning code on Jupyter for multiple images

Retraining the captioning model

Summary

Reading License Plates with OpenCV

Identifying the license plate

Plate utility functions

The gray_thresh_img function and morphological functions

Kernels

The matching character function

The k-nearest neighbors digit classifier

Finding plate characters

Finding matches and groups of characters

Finding and reading license plates with OpenCV

Result analysis

Summary

Human Pose Estimation with TensorFlow

Pose estimation using DeeperCut and ArtTrack

Single-person pose detection

Multi-person pose detection

Retraining the human pose estimation model

Summary

Handwritten Digit Recognition with scikit-learn and TensorFlow

Acquiring and processing MNIST digit data

Creating and training a support vector machine

Applying the support vector machine to new data

Introducing TensorFlow with digit classification

Evaluating the results

Summary

Facial Feature Tracking and Classification with dlib

Introducing dlib

Facial landmarks

Finding 68 facial landmarks in images

Faces in videos

Facial recognition

Summary

Deep Learning Image Classification with TensorFlow

Technical requirements

An introduction to TensorFlow

Using Inception for image classification

Retraining with our own images

Speeding up computation with your GPU

Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think