Book Image

Machine Learning for OpenCV

By : Michael Beyeler
Book Image

Machine Learning for OpenCV

By: Michael Beyeler

Overview of this book

Machine learning is no longer just a buzzword, it is all around us: from protecting your email, to automatically tagging friends in pictures, to predicting what movies you like. Computer vision is one of today's most exciting application fields of machine learning, with Deep Learning driving innovative systems such as self-driving cars and Google’s DeepMind. OpenCV lies at the intersection of these topics, providing a comprehensive open-source library for classic as well as state-of-the-art computer vision and machine learning algorithms. In combination with Python Anaconda, you will have access to all the open-source computing libraries you could possibly ask for. Machine learning for OpenCV begins by introducing you to the essential concepts of statistical learning, such as classification and regression. Once all the basics are covered, you will start exploring various algorithms such as decision trees, support vector machines, and Bayesian networks, and learn how to combine them with other OpenCV functionality. As the book progresses, so will your machine learning skills, until you are ready to take on today's hottest topic in the field: Deep Learning. By the end of this book, you will be ready to take on your own machine learning problems, either by building on the existing source code or developing your own algorithm from scratch!
Table of Contents (13 chapters)

Understanding the perceptron

In the 1950s, American psychologist and artificial intelligence researcher Frank Rosenblatt invented an algorithm that would automatically learn the optimal weight coefficients w0 and w1 needed to perform an accurate binary classification: the perceptron learning rule.

Rosenblatt's original perceptron algorithm can be summed up as follows:

  1. Initialize the weights to zero or some small random numbers.
  2. For each training sample si, perform the following steps:
    1. Compute the predicted target value ŷi.
    2. Compare ŷi to the ground truth yi, and update the weights accordingly:
      • If the two are the same (correct prediction), skip ahead.
      • If the two are different (wrong prediction), push the weight coefficients w0 and w1 towards the positive or negative target class respectively.

Let's have a closer look at the last step, which is the weight...