Eigenfaces is a computer vision technique developed in 1991 by M. Turk and A.Pentland used to distinguish an image of a face with only a single 2D image. The purpose of this project was to develop a system capable of automatically recognizing and tracking a face throughout a real-time video using the Eigenfaces technique. These techniques take advantage of the assumptions that faces share relatively the same features and are usually upright. The Eigenfaces technique transforms several images of individual faces from an image into vectors based on the pixel values contained within the image. The vectors are then used to create an n-dimensional space in which future images can be placed to determine the likelihood the image contains a face. This project segments a single image into a grid and applies the Eigenface technique to each segment rather than the entire image. The result of this process is the successful application to each image in a video to track the movement of a face throughout the video in real time.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.