Computer Vision With Python 3 by Kapur, Saurabh -- Read -- Imperial Library of Trantor

Index

Preface

What this book covers What you need for this book Who this book is for Conventions Reader feedback Customer support

Downloading the example code Downloading the color images of this book Errata Piracy Questions

Introduction to Image Processing

Image processing - its applications Image processing libraries

Pillow

Installation Getting started with pillow

Reading an image Writing or saving an image Cropping an image Changing between color spaces Geometrical transformation Image enhancement

Introduction to scikit-image

Installation Getting started with scikit-image

Summary

Filters and Features

Image derivatives

Kernels

Convolution Understanding image filters

Gaussian blur Median filter Dilation and erosion

Erosion Dilation

Custom filters Image thresholding

Edge detection

Sobel edge detector

Why have pixels with large gradient values?

Canny edge detector Hough line Hough circle

Summary

Drilling Deeper into Features - Object Detection

Revisiting image features Harris corner detection Local Binary Patterns Oriented FAST and Rotated BRIEF (ORB)

oFAST – FAST keypoint orientation FAST detector Orientation by intensity centroid rBRIEF – Rotation-aware BRIEF Steered BRIEF Variance and correlation

Image stitching Summary

Segmentation - Understanding Images Better

Introduction to segmentation Contour detection The Watershed algorithm Superpixels Normalized graph cut Summary

Integrating Machine Learning with Computer Vision

Introduction to machine learning

Data preprocessing

Image translation through random cropping Image rotation and scaling

Scikit-learn (sklearn)

Applications of machine learning for computer vision Logistic regression Support vector machines K-means clustering Summary

Image Classification Using Neural Networks

Introduction to neural networks

Design of a basic neural network Training a network MNIST digit classification using neural networks Playing with hidden layers

Convolutional neural networks Challenges in machine learning Summary

Introduction to Computer Vision using OpenCV

Installation

macOS Windows Linux

OpenCV APIs

Reading an image

Writing/saving the image Changing the color space Scaling Cropping the image Translation Rotation Thresholding Filters

Gaussian blur Median blur

Morphological operations

Erosion Dilation

Edge detection

Sobel edge detection Canny edge detector

Contour detection Template matching

Summary

Object Detection Using OpenCV

Haar Cascades

Integral images

Scale Invariant Feature Transformation (SIFT)

Algorithm behind SIFT

Scale-space extrema detection Keypoint localization Orientation assignment Keypoint descriptor

Speeded up robust features

Detecting SURF keypoints SURF keypoint descriptors

Orientation assignment Descriptor based on Haar wavelet response

Summary

Video Processing Using OpenCV

Reading/writing videos

Reading a video Writing a video

Basic operations on videos

Converting to grayscale

Color tracking Object tracking

Kernelized Correlation Filter (KCF) Lucas Kanade Tracker (LK Tracker)

Summary

Computer Vision as a Service

Computer vision as a service – architecture overview Environment setup

http-server virtualenv flask

Developing a server-client model

Client Server

Computer vision engine Putting it all together

Client Server

Summary

← Prev
Back
Next →

← Prev
Back
Next →