Module 2 is about understanding and preparing images for input into machine learning (ML) models. This module lets you explore the various preprocessing techniques used for image preparation, pixel value acquisition, and more.
Image preprocessing manipulates images to increase the readability and amount of available data that can be used in a ML training set. This activity introduces common techniques used for image preprocessing.
OpenCV is a free open-source library of code and functions used for computer vision, image processing, and machine learning. This activity introduces various methods of image manipulation using the OpenCV library.
Images are built through a matrix of data stored in indexes, known more commonly as pixels. This activity discusses the concepts of pixel indexes and how they form the images we see in our everyday lives.
A pixel relays color information through numerical values, commonly called the pixel's intensities. This activity investigates various methods used for analyzing pixel's intensities and their effects on image outputs.
There are many ways for a computer to understand or display information through the layering of colored pixels. This activity introduces a few common color systems and concepts necessary to switch between them.