What this book covers

Chapter 1, Building an Image Viewer, covers building our first application with Qt. We will build an image viewer, with which we can browse images in a folder. We'll also be able to zoom in or out of the image while viewing it.

Chapter 2, Editing Images Like a Pro, combines the Qt library and the OpenCV library to build a new application, an image editor. In this chapter, we will start by blurring an image to learn how to edit an image. Then, we will learn how to use many other editing effects, such as eroding, sharpening, cartoon effects, and geometric transformation. Each of these features will be incorporated as a Qt plugin, so the plugin mechanism of the Qt library will also be covered.

Chapter 3, Home Security Applications, covers building an application for home security. With a webcam, this application can detect motion and send notifications to a mobile phone upon motion being detected. We will learn how to deal with cameras and videos, how to analyze motion and detect movement with OpenCV, and how to send notifications via IFTTT in this chapter.

Chapter 4, Fun with Faces, explores how to detect faces and facial landmarks with OpenCV. We will build an application to detect faces and facial landmarks in the video in real time in this chapter, and, with the facial landmarks detected, we will apply some funny masks to the faces.

Chapter 5, Optical Character Recognition, introduces the Tesseract library to you. With the help of this library, we will extract text from images such as photos of book pages and scanned documents. In order to extract text from photos of common scenes, we will use a deep learning model named EAST to detect the text areas in photos, and then pass those areas to the Tesseract library. In order to extract text on the screen conveniently, we will also learn how to grab the screen as an image with the Qt library.

Chapter 6, Object Detection in Real Time, shows how to use cascade classifiers to detect objects. Besides using pretrained classifiers, we will also learn how to train classifiers by ourselves. Then, we will introduce how to detect objects by using deep learning models, and a model named YOLOv3 will be used to demonstrate the usage of this approach.

Chapter 7, Real-Time Car Detection and Distance Measurement, covers creating an application to detect cars and measure distances. In the application, we will learn how to measure distances between objects from a bird's eye view and how to measure distances between objects and the camera at eye level view.

Chapter 8, Using OpenGL for High-Speed Filtering of Images, the final chapter of the book, introduces an approach to heterogeneous computing. In this chapter, we first have a brief introduction to the OpenGL specification, and then use it to filter images on the GPU. This is not a typical way to use OpenGL, and it is not typical to do heterogeneous computing either, so we can refer to OpenCL or CUDA if we want to do heterogeneous computing in a mature way.

Appendix A, Assessments, contains answers to all the assessment questions.