We received feedback from people who bought the first edition of the book and also from experts in the topic while working on the second edition of the book.

We added three new chapters and one new appendix. When the first edition was written, machine learning (ML) and deep learning (DL) were not yet mainstream. Today, problems that cannot be solved by using traditional image processing and computer vision techniques are being solved using ML and DL. So we added one chapter on neural network and another chapter on convolutional neural network (CNN). In these two chapters, we discuss the mathematical underpinnings of these two networks. We also discuss solving these two networks using Keras, a ML / DL library.

We also added a new chapter on affine transformation, a geometric transformation that preserves lines. We also added an appendix on parallel computing using joblib, a Python module that allows distributing tasks to multiple Python process that can run on multiple cores on a given computer.

We added new algorithms to existing chapters and also improved the explanation of the code. Some of the new algorithms introduced are Frangi filter, Contrast Limited Adaptive Histogram Equalization (CLAHE), Local contrast normalization, Chan-Vese segmentation, Gray scale morphology etc.

When the first edition was written, we used Python 2.7 for testing the code. As of January 2020, Python 2.7 is no longer supported. So we modified the code for the latest version of Python 3. We also modified the code for the latest version of numpy, scipy, scikit and OpenCV.

We hope you enjoy learning from the book.

MATLAB^® is a registered trademark of The MathWorks, Inc. For product information, please contact:

The MathWorks, Inc.

3 Apple Hill Drive

Natick, MA 01760-2098 USA

Tel: 508-647-7000

Fax: 508-647-7001

E-mail: [email protected]

Web: www.mathworks.com