Preprocessing of images

The first step in our pipeline is face detection. We will then align the faces, extract features, and then finalize our preprocessing on Docker.

Face detection

Obviously, it's very important to first locate the faces in the given photograph so that they can be fed into the later part of the pipeline. There are lots of ways to detect faces, such as detecting skin textures, oval/round shape detection, and other statistical methods. We're going to use a method called HOG.

HOG is a feature descriptor that represents the distribution (histograms) of directions of gradients (oriented gradients), which are used as features. Gradients (x and y derivatives) of an image are useful, because the magnitude...