Computer vision is the study and design of computational artifacts for processing and understanding images. These artifacts sometimes employ machine learning. An overview of computer vision is far beyond the scope of this book, but in this section, we will review some basic techniques used in computer vision for representing images in machine learning problems.
A digital image is usually a raster, or pixmap, that maps colors to coordinates on a grid. That is, an image can be viewed as a matrix in which each element represents a color. A basic feature representation for an image can be constructed by reshaping the matrix into a vector by concatenating its rows together. Optical Character Recognition (OCR) is a canonical machine learning problem. Let's use this technique to create basic feature representations that can be used in an OCR application to recognize hand-written digits in character-delimited forms.
The digits...