OpenCV with Python Blueprints电子书

OpenCV with Python Blueprints

Table of Contents

OpenCV with Python Blueprints

Credits

About the Author

About the Reviewers

www.PacktPub.com

Support files, eBooks, discount offers, and more

Why subscribe?

Free access for Packt account holders

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

1. Fun with Filters

Planning the app

Creating a black-and-white pencil sketch

Implementing dodging and burning in OpenCV

Pencil sketch transformation

Generating a warming/cooling filter

Color manipulation via curve shifting

Implementing a curve filter by using lookup tables

Designing the warming/cooling effect

Cartoonizing an image

Using a bilateral filter for edge-aware smoothing

Detecting and emphasizing prominent edges

Combining colors and outlines to produce a cartoon

Putting it all together

Running the app

The GUI base class

The GUI constructor

Handling video streams

A basic GUI layout

A custom filter layout

Summary

2. Hand Gesture Recognition Using a Kinect Depth Sensor

Planning the app

Setting up the app

Accessing the Kinect 3D sensor

Running the app

The Kinect GUI

Tracking hand gestures in real time

Hand region segmentation

Finding the most prominent depth of the image center region

Applying morphological closing to smoothen the segmentation mask

Finding connected components in a segmentation mask

Hand shape analysis

Determining the contour of the segmented hand region

Finding the convex hull of a contour area

Finding the convexity defects of a convex hull

Hand gesture recognition

Distinguishing between different causes of convexity defects

Classifying hand gestures based on the number of extended fingers

Summary

3. Finding Objects via Feature Matching and Perspective Transforms

Tasks performed by the app

Planning the app

Setting up the app

Running the app

The FeatureMatching GUI

The process flow

Feature extraction

Feature detection

Detecting features in an image with SURF

Feature matching

Matching features across images with FLANN

The ratio test for outlier removal

Visualizing feature matches

Homography estimation

Warping the image

Feature tracking

Early outlier detection and rejection

Seeing the algorithm in action

Summary

4. 3D Scene Reconstruction Using Structure from Motion

Planning the app

Camera calibration

The pinhole camera model

Estimating the intrinsic camera parameters

The camera calibration GUI

Initializing the algorithm

Collecting image and object points

Finding the camera matrix

Setting up the app

The main function routine

The SceneReconstruction3D class

Estimating the camera motion from a pair of images

Point matching using rich feature descriptors

Point matching using optic flow

Finding the camera matrices

Image rectification

Reconstructing the scene

3D point cloud visualization

Summary

5. Tracking Visually Salient Objects

Planning the app

Setting up the app

The main function routine

The Saliency class

The MultiObjectTracker class

Visual saliency

Fourier analysis

Natural scene statistics

Generating a Saliency map with the spectral residual approach

Detecting proto-objects in a scene

Mean-shift tracking

Automatically tracking all players on a soccer field

Extracting bounding boxes for proto-objects

Setting up the necessary bookkeeping for mean-shift tracking

Tracking objects with the mean-shift algorithm

Putting it all together

Summary

6. Learning to Recognize Traffic Signs

Planning the app

Supervised learning

The training procedure

The testing procedure

A classifier base class

The GTSRB dataset

Parsing the dataset

Feature extraction

Common preprocessing

Grayscale features

Color spaces

Speeded Up Robust Features

Histogram of Oriented Gradients

Support Vector Machine

Using SVMs for Multi-class classification

Training the SVM

Testing the SVM

Confusion matrix

Accuracy

Precision

Recall

Putting it all together

Summary

7. Learning to Recognize Emotions on Faces

Planning the app

Face detection

Haar-based cascade classifiers

Pre-trained cascade classifiers

Using a pre-trained cascade classifier

The FaceDetector class

Detecting faces in grayscale images

Preprocessing detected faces

Facial expression recognition

Assembling a training set

Running the screen capture

The GUI constructor

The GUI layout

Processing the current frame

Adding a training sample to the training set

Dumping the complete training set to a file

Feature extraction

Preprocessing the dataset

Principal component analysis

Multi-layer perceptrons

The perceptron

Deep architectures

An MLP for facial expression recognition

Training the MLP

Testing the MLP

Running the script

Putting it all together

Summary

Index