Book Image

OpenCV 3 Computer Vision with Python Cookbook

By : Aleksei Spizhevoi, Aleksandr Rybnikov

Book Image

OpenCV 3 Computer Vision with Python Cookbook

By: Aleksei Spizhevoi, Aleksandr Rybnikov

Overview of this book

OpenCV 3 is a native cross-platform library for computer vision, machine learning, and image processing. OpenCV's convenient high-level APIs hide very powerful internals designed for computational efficiency that can take advantage of multicore and GPU processing. This book will help you tackle increasingly challenging computer vision problems by providing a number of recipes that you can use to improve your applications. In this book, you will learn how to process an image by manipulating pixels and analyze an image using histograms. Then, we'll show you how to apply image filters to enhance image content and exploit the image geometry in order to relay different views of a pictured scene. We’ll explore techniques to achieve camera calibration and perform a multiple-view analysis. Later, you’ll work on reconstructing a 3D scene from images, converting low-level pixel information to high-level concepts for applications such as object detection and recognition. You’ll also discover how to process video from files or cameras and how to detect and track moving objects. Finally, you'll get acquainted with recent approaches in deep learning and neural networks. By the end of the book, you’ll be able to apply your skills in OpenCV to create computer vision applications in various domains.

Preface

Who this book is for

What this book covers

To get the most out of this book

Free Chapter

I/O and GUI

Reading images from files

Simple image transformations—resizing and flipping

Saving images using lossy and lossless compression

Showing images in an OpenCV window

Working with UI elements, such as buttons and trackbars, in an OpenCV window

Drawing 2D primitives—markers, lines, ellipses, rectangles, and text

Handling user input from a keyboard

Making your app interactive through handling user input from a mouse

Capturing and showing frames from a camera

Playing frame stream from video

Obtaining a frame stream properties

Writing a frame stream into video

Jumping between frames in video files

Matrices, Colors, and Filters

Matrices, Colors, and Filters

Manipulating matrices-creating, filling, accessing elements, and ROIs

Converting between different data types and scaling values

Non-image data persistence using NumPy

Manipulating image channels

Converting images from one color space to another

Gamma correction and per-element math

Mean/variance image normalization

Computing image histograms

Equalizing image histograms

Removing noise using Gaussian, median, and bilateral filters

Computing gradients using Sobel operator

Creating and applying your own filter

Processing images with real-valued Gabor filters

Going from the spatial domain to the frequency domain (and back) using the discrete Fourier transform

Manipulating image frequencies for image filtration

Processing images with different thresholds

Morphological operators

Image masks and binary operations

Contours and Segmentation

Contours and Segmentation

Binarization of grayscale images using the Otsu algorithm

Finding external and internal contours in a binary image

Extracting connected components from a binary image

Fitting lines and circles into two-dimensional point sets

Calculating image moments

Working with curves - approximation, length, and area

Checking whether a point is within a contour

Computing distance maps

Image segmentation using the k-means algorithm

Image segmentation using segment seeds - the watershed algorithm

Object Detection and Machine Learning

Object Detection and Machine Learning

Obtaining an object mask using the GrabCut algorithm

Finding edges using the Canny algorithm

Detecting lines and circles using the Hough transform

Finding objects via template matching

The medial flow tracker

Tracking objects using different algorithms via the tracking API

Computing the dense optical flow between two frames

Detecting chessboard and circle grid patterns

A simple pedestrian detector using the SVM model

Optical character recognition using different machine learning models

Detecting faces using Haar/LBP cascades

Detecting AruCo patterns for AR applications

Detecting text in natural scenes

QR code detector

Deep Learning

Representing images as tensors/blobs

Loading deep learning models from Caffe, Torch, and TensorFlow formats

Getting input and output tensors' shapes for all layers

Preprocessing images and inference in convolutional networks

Measuring inference time and contributions to it from each layer

Classifying images with GoogleNet/Inception and ResNet models

Detecting objects with the Single Shot Detection (SSD) model

Segmenting a scene using the Fully Convolutional Network (FCN) model

Face detection using Single Shot Detection (SSD) and the ResNet model

Age and gender prediction

Linear Algebra

The orthogonal Procrustes problem

Rank-constrained matrix approximation

Principal component analysis

Solving systems of linear equations (including under- and over-determined)

Solving polynomial equations

Linear programming with the simplex method

Detectors and Descriptors

Detectors and Descriptors

Finding corners in an image - Harris and FAST

Selecting good corners in an image for tracking

Drawing keypoints, descriptors, and matches

Detecting scale invariant keypoints

Computing descriptors for image keypoints - SURF, BRIEF, ORB

Matching techniques for finding correspondences between descriptors

Finding reliable matches - cross-check and ratio test

Model-based filtering of matches - RANSAC

BoW model for constructing global image descriptors

Image and Video Processing

Image and Video Processing

Warping an image using affine and perspective transformations

Remapping an image using arbitrary transformation

Tracking keypoints between frames using the Lucas-Kanade algorithm

Background subtraction

Stitching many images into panorama

Denoising a photo using non-local means algorithms

Constructing an HDR image

Removing defects from a photo with image inpainting

Multiple View Geometry

Multiple View Geometry

Pinhole camera model calibration

Fisheye camera model calibration

Stereo rig calibration - estimation of extrinsics

Distorting and undistorting points

Removing lens distortion effects from an image

Restoring a 3D point from two observations through triangulation

Finding a relative camera-object pose through the PnP algorithm

Aligning two views through stereo rectification

Epipolar geometry - computing fundamental and essential matrices

Essential matrix decomposition into rotation and translation

Estimating disparity maps for stereo images

Special case 2-view geometry - estimating homography transformation

Planar scene - decomposing homography into rotation and translation

Rotational camera case - estimating camera rotation from homography

Other Books You May Enjoy

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

5 star

0

4 star

0

3 star

0

2 star

0

1 star

0

Matrices, Colors, and Filters

In this chapter, we will cover the following recipes:

Manipulating matrices-creating, filling, accessing elements, and ROIs
Converting between different data types and scaling values
Non-image data persistence using NumPy
Manipulating image channels
Converting images from one color space to another
Gamma correction and per-element math
Mean/variance image normalization
Computing image histograms
Equalizing image histograms
Removing noise using Gaussian, median, and bilateral filters
Computing gradient images using Sobel filters
Creating and applying your own filter
Processing images with real-valued Gabor filters
Going from the spatial to the frequency domain (and back) using discrete Fourier transform
Manipulating image frequencies for image filtration
Processing images with different thresholds
Morphological operators
Binary images-image masks...