Chapter 1, Introduction to Image Processing, as the name suggests, introduces the reader to the basics of image processing. Starting with some common use cases of image processing, the chapter goes on to explain how to install different image processing libraries. The next few sections in the chapter explain how to read/write an image and perform basic image manipulation operations.

Chapter 2, Filters and Features, gives the reader an overview of what filters and features mean in the context of computer vision. We start with convolution, which forms the basis of applying any filter to an image. Then we look at some common filters, such as Gaussian Blur and Median Blur. The second half of the chapter explains the basic image features and how they are implemented using Python.

Chapter 3, Drilling Deeper into Features – Object Detection, walks the reader through some of the sophisticated image feature extraction algorithms, such as Local Binary Pattern and ORB. These algorithms help to identify objects in an image and match them with other images that have the same objects in them. Such matching algorithms form the basis of the most complex computer vision algorithms.

Chapter 4, Segmentation – Understanding Images Better, has a different theme than the last two chapters. This chapter looks at different image segmentation algorithms, namely, contour detection, superpixels, watershed, and normalized graph cut. These algorithms are fairly easy to implement and run in almost real time. Image segmentation can be use in real-world applications such as background subtraction, image understanding, and scene labeling. Recent advances in machine learning, especially deep learning, have enabled more sophisticated methods of image segmentation that involve almost no manual tuning of parameters.

Chapter 5, Integrating Machine Learning with Computer Vision, brings together two different fields together. This chapter shows how machine learning algorithms can be implemented for images. We implement a classic image classification program for digit recognition.

Chapter 6, Image Classification Using Neural Networks, is an extension of the last chapter. In this chapter, we implement digit classification using advanced machine learning technique called neural networks. We install a new library called Keras to implement the neural network.

Chapter 7, Introduction to Computer Vision Using OpenCV, introduces the readers to a new computer vision library called OpenCV. In this chapter, we revisit all the image processing concepts and algorithms that we have read so far in the book and implement them using OpenCV.

Chapter 8, Object Detection Using OpenCV, explains different feature extraction algorithms and we will be using OpenCV to implement all the algorithms.

Chapter 9, Video Processing Using OpenCV, explains how to work with videos instead of images. The chapter uses code snippets to walk the reader through how to capture and save a video. It then explains how to perform operations such as resizing and changing the color space in videos. In the last section, we see how to implement object tracking in videos.

Chapter 10, Computer Vision as a Service, is the last chapter and it provides an overview of how production-scale computer vision systems are built. The chapter focuses on the infrastructure that is needed for computer vision algorithms. A simple computer vision service is implemented, giving the readers a flavor of how services such as Google Image search are built.

The software required for this book are as follows:

The book is ideal for developers who have basic knowledge of Python and want to build a strong foundation in implementing computer vision algorithms. The book is also suitable for developers with theoretical knowledge of computer vision but who lack the experience of implementing the algorithms.

In this book, you will find a number of styles of text that distinguish between different kinds of information. Here are some examples of these styles, and an explanation of their meaning.

Code words in text, database table names, folder names, filenames, file extensions, pathnames, dummy URLs, user input, and Twitter handles are shown as follows:

"To save or write an image we can use the imsave() function."

A block of code is set as follows:

>>> from PIL import Image
>>> img = Image.open("image.png")
>>> img.getpixel((100,100))
output
(150, 188, 233, 255)
>>> img.convert("L").getpixel((100,100))

When we wish to draw your attention to a particular part of a code block, the relevant lines or items are set in bold:

>>> from skimage import io
 >>> img = io.imread("image.png")
 >>> io.imshow("image.png")
 >>> io.show()

Any command-line (including commands in the R console) input or output is written as follows:

$: pip install Pillow

New terms and important words are shown in bold. Words that you see on the screen, in menus or dialog boxes, for example, appear in the text like this: "Clicking the Next button moves you to the next screen."

Feedback from our readers is always welcome. Let us know what you think about this book-what you liked or disliked. Reader feedback is important to us as it helps us develop titles that you will really get the most out of. To send us general feedback, simply email [email protected], and mention the book's title in the subject of your message. If there is a topic that you have expertise in and you are interested in either writing or contributing to a book, see our author guide at www.packtpub.com/authors.

Now that you are the proud owner of a Packt book, we have a number of things to help you to get the most from your purchase.