Consider the problem of detecting human faces in images of larger scenes that may contain one or
Question:
Consider the problem of detecting human faces in images of larger scenes that may contain one or more faces, or no faces at all. The specific goal is to identify the location and size of each face in an image, rather than merely determining whether a face is present in the image. Suppose you are given as training data a set of images in which all of the faces have been labeled (specified as a list of pixel positions for each face). Describe one approach to solving this problem using binary classification machine learning. Specify what will serve as training examples for the binary classification algorithm, and how the binary classifier can be used to detect faces in new images. You don’t need to specify the specific features or classification algorithm to use.
Step by Step Answer:
Artificial Intelligence A Modern Approach
ISBN: 9780134610993
4th Edition
Authors: Stuart Russell, Peter Norvig