Histogram of Oriented Gradients (HoG) features

Histogram of Oriented Gradients, or HoG is a common method of feature extraction that works on detecting edges in the image.

In short, HoG constructs a histogram of edges detected at certain angles within each square of a grid laid over the image. This video explains the process in more detail.

For more on edge detection, and other types of image segmentation, see our previous course Introduction to Image Analysis for Plant Phenotyping.