As discussed in Chapter 7, Extracting Image Features and Descriptors, a Histogram of Oriented Gradients (HOG) is a feature descriptor used in a variety of computer vision and image processing applications for the purposes of object detection. HOG descriptors were first used along with the SVM classifier for pedestrian detection by Navneet Dalal and Bill Triggs. The use of HOG descriptors has been a particularly successful technique in detecting, among other things, humans, animals, faces, and text. For example, an object detection system can be considered for generating HOG descriptors that describe features of objects in an input image.
We already described how to compute a HOG descriptor from ...