To get the most out of this book

Basic knowledge of Python and image processing is required to understand and run the code, along with access to a few online image datasets and the book's GitHub link.

Python 3.5+ (Python 3.7.4 was used to test the code) is needed with Anaconda preferably installed for the Windows users, along with Jupyter (to view/run notebooks).

All the code was tested on Windows 10 (Pro) with 32 GB RAM and an Intel i7-series processor. However, the code should require little/no change to be run on Linux.

You will need to install all the required Python packages using pip3.

Access to a GPU is recommended to run the recipes involving training with deep learning (that is, training that involves libraries such as TensorFlow, Keras, and PyTorch) much faster. The code that is best run with a GPU was tested on an Ubuntu 16.04 machine with an Nvidia Tesla K80 GPU (with CUDA 10.1).

A basic math background is also needed to understand the concepts in the book.

Software/hardware covered in the book	OS requirements
Python 3.7.4.	Windows 10.
Anaconda version 2019.10 (py37_0).	Windows 10.
For the GPU, you will need an NVIDIA graphics card or access to an AWS GPU instance (https://docs.aws.amazon.com/dlami/latest/devguide/gpu.html) or Google Colab (https://colab.research.google.com/).	Windows 10/Linux (Ubuntu 16).

If you are using the digital version of this book, we advise you to type the code yourself or access the code via the GitHub repository (link available in the next section). Doing so will help you avoid any potential errors related to the copying and pasting of code.

To access the notebooks and images, clone the repository from this URL: https://github.com/PacktPublishing/Python-Image-Processing-Cookbook.

Install Python 3.7 and the necessary libraries as and when required. Install Anaconda/Jupyter and open the notebooks for each chapter. Run the code for each recipe. Follow the instructions for each recipe for any additional steps (for instance, you may need to download a pre-trained model or an image dataset).

Some additional exercises are provided for most of the recipes in a There's more... section to test your understanding. Perform them independently and have fun!

Download the example code files

You can download the example code files for this book from your account at www.packt.com. If you purchased this book elsewhere, you can visit www.packtpub.com/support and register to have the files emailed directly to you.

You can download the code files by following these steps:

1. Log in or register at www.packt.com.
2. Select the Support tab.
3. Click on Code Downloads.
4. Enter the name of the book in the Search box and follow the onscreen instructions.

Once the file is downloaded, please make sure that you unzip or extract the folder using the latest version of:

• WinRAR/7-Zip for Windows
• Zipeg/iZip/UnRarX for Mac
• 7-Zip/PeaZip for Linux

The code bundle for the book is also hosted on GitHub at https://github.com/PacktPublishing/Python-Image-Processing-Cookbook. In case there's an update to the code, it will be updated on the existing GitHub repository.

We also have other code bundles from our rich catalog of books and videos available at https://github.com/PacktPublishing/. Check them out!

Download the color images

We also provide a PDF file that has color images of the screenshots/diagrams used in this book. You can download it here: https://static.packt-cdn.com/downloads/9781789537147_ColorImages.pdf.

Conventions used

There are a number of text conventions used throughout this book.

CodeInText: Indicates code words in text, database table names, folder names, filenames, file extensions, pathnames, dummy URLs, user input, and Twitter handles. Here is an example: "Implement a bilinear_interpolate() function, which interpolates over every image channel."

A block of code is set as follows:

def get_grid_coordinates(points):
  xmin, xmax = np.min(points[:, 0]), np.max(points[:, 0]) + 1
  ymin, ymax = np.min(points[:, 1]), np.max(points[:, 1]) + 1
  return np.asarray([(x, y) for y in range(ymin, ymax)
         for x in range(xmin, xmax)], np.uint32)

Any command-line input or output is written as follows:

$ pip install mtcnn

Bold: Indicates a new term, an important word, or words that you see onscreen. For example, words in menus or dialog boxes appear in the text like this. Here is an example: "Face alignment is a data normalization process—an essential preprocessing step for many facial recognition algorithms."

Warnings or important notes appear like this.

Tips and tricks appear like this.