From the point of view of the computer, an image is a large rectangular array of pixel values. Our goal is to process one or more image and to arrive at a decision for our application.

Depending on the setting, it may be a classification problem, a clustering problem, or any of the other problem classes we have seen in the book.

The first step will be to load the image from disk, where it is typically stored in an image-specific format such as PNG or JPEG, the former being a lossless compression format and the latter a lossy compression, one that is optimized for visual assessment of photographs. Then, we may wish to perform preprocessing on the images (for example, normalizing them for illumination variations).