万本电子书0元读

万本电子书0元读

顶部广告

Hands-On Computer Vision with Julia电子书

售       价:¥

75人正在读 | 0人评论 9.8

作       者:Dmitrijs Cudihins

出  版  社:Packt Publishing

出版时间:2018-06-29

字       数:19.8万

所属分类: 进口书 > 外文原版书 > 电脑/网络

温馨提示:此类商品不支持退换货,不支持下载打印

为你推荐

  • 读书简介
  • 目录
  • 累计评论(0条)
  • 读书简介
  • 目录
  • 累计评论(0条)
Explore the various packages in Julia that support image processing and build neural networks for video processing and object tracking. About This Book ? Build a full-fledged image processing application using JuliaImages ? Perform basic to advanced image and video stream processing with Julia's APIs ? Understand and optimize various features of OpenCV with easy examples Who This Book Is For Hands-On Computer Vision with Julia is for Julia developers who are interested in learning how to perform image processing and want to explore the field of computer vision. Basic knowledge of Julia will help you understand the concepts more effectively. What You Will Learn ? Analyze image metadata and identify critical data using JuliaImages ? Apply filters and improve image quality and color schemes ? Extract 2D features for image comparison using JuliaFeatures ? Cluster and classify images with KNN/SVM machine learning algorithms ? Recognize text in an image using the Tesseract library ? Use OpenCV to recognize specific objects or faces in images and videos ? Build neural network and classify images with MXNet In Detail Hands-On Computer Vision with Julia is a thorough guide for developers who want to get started with building computer vision applications using Julia. Julia is well suited to image processing because it’s easy to use and lets you write easy-to-compile and efficient machine code. This book begins by introducing you to Julia's image processing libraries such as Images.jl and ImageCore.jl. You’ll get to grips with analyzing and transforming images using JuliaImages; some of the techniques discussed include enhancing and adjusting images. As you make your way through the chapters, you’ll learn how to classify images, cluster them, and apply neural networks to solve computer vision problems. In the concluding chapters, you will explore OpenCV applications to perform real-time computer vision analysis, for example, face detection and object tracking. You will also understand Julia's interaction with Tesseract to perform optical character recognition and build an application that brings together all the techniques we introduced previously to consolidate the concepts learned. By end of the book, you will have understood how to utilize various Julia packages and a few open source libraries such as Tesseract and OpenCV to solve computer vision problems with ease. Style and approach Readers will be taken through various packages that support image processing in Julia, and will also tap into open-source libraries such as Open CV and Tesseract to find the optimum solution to problems encountered in computer vision.
目录展开

Title Page

Copyright and Credits

Hands-On Computer Vision with Julia

Packt Upsell

Why subscribe?

PacktPub.com

Contributors

About the author

About the reviewer

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

Getting Started with JuliaImages

Technical requirements

Setting up your Julia

Installing packages

Reading images

Reading a single image from disk

Reading a single image from a URL

Reading images in a folder

Saving images

Using test images

Previewing images

Cropping, scaling, and resizing

Cropping an image

Resizing an image

Scaling an image

Scaling by percentage

Scaling to a specific dimension

Scaling by two-fold

Rotating images

Summary

Questions

Image Enhancement

Technical requirements

Images as arrays

Accessing pixels

Converting images into arrays of numbers

Converting arrays of numbers into colors

Changing color saturation

Converting an image to grayscale

Creating a custom color filter

Applying image filters

Padding images

Padding with a constant value

Padding by duplicating content from an image

Blurring images

Sharpening images

Summary

Questions

Image Adjustment

Technical requirements

Image binarization

Fundamental operations

Image erosion

Object separation using erosion

Image preparation for text recognition

Image dilation

Merging almost-connected objects

Highlighting details

Derived operations

Image opening

Image closing

Top-hat and bottom-hat operation

Adjusting image contrast

Summary

Questions

Image Segmentation

Technical requirements

Supervised methods

Seeded region growing

Identifying a simple object

Identifying a complex object

Unsupervised methods

The graph-based approach

The fast scanning approach

Helper functions

Summary

Questions

Further reading

Image Representation

Technical requirements

Understanding features and descriptors

FAST corner detection

Corner detection using the imcorner function

Comparing performance

BRIEF – efficient duplicate detection method

Identifying image duplicates

Creating a panorama from many images

ORB, rotation invariant image matching

BRISK – scale invariant image matching

FREAK – fastest scale and rotation invariant matching

Running face recognition

Summary

Questions

Introduction to Neural Networks

Technical requirements

Introduction

The need for neural networks

The need for MXNet

First steps with the MNIST dataset

Getting the data

Preparing the data

Defining a neural network

Fitting the network

Improving the network

Predicting new images

Putting it all together

Multiclass classification with the CIFAR-10 dataset

Getting and previewing the dataset

Preparing the data

Starting with the linear classifier

Reusing the MNIST architecture

Improving the network

Accuracy – why at almost 70

Putting it all together

Classifying cats versus dogs

Getting and previewing the dataset

Creating an image data iterator

Training the model

Putting it all together

Reusing your models

Saving the model

Loading the model

Summary

Questions

Further reading

Using Pre-Trained Neural Networks

Technical requirements

Introduction to pre-trained networks

Transfer learning

MXNet Model Zoo

Predicting image classes using Inception V3

Setting up the Inception V3 environment

Loading the network

Preparing the datasets

Running predictions

Expected performance

Putting it all together

Predicting an image class using MobileNet V2

Setting up the environment

Loading the network

Preparing the datasets

Running the predictions

Expected performance

Putting it all together

Extracting features generated by Inception V3

Preparing the network

Removing the last Softmax and FullyConnected layers

Predicting features of an image

Saving the network to disk

Extracting features generated by MobileNet V2

Preparing the network

Removing the last Softmax and FullyConnected layers

Predicting features of an image

Saving the network to disc

Putting it all together

Transfer learning with Inception V3

Getting the data

Preparing the dataset

Extracting features

Creating a new network

Training and validating the results

Summary

Questions

Further reading

OpenCV

Technical requirements

Troubleshooting installation of Open CV

Troubleshooting installation on macOS

First steps with OpenCV

Updating OpenCV package source code

Defining Open CV location

Testing whether OpenCV works

Working with images

Converting OpenCV Mat to Julia images

Reading images

Saving images

Destroying the object

Image capturing from web camera

Face detection using Open CV

Object detection using MobileNet-SSD

Summary

Questions

Assessments

Other Books You May Enjoy

Leave a review - let other readers know what you think

累计评论(0条) 0个书友正在讨论这本书 发表评论

发表评论

发表评论,分享你的想法吧!

买过这本书的人还买过

读了这本书的人还在读

回顶部