Eigenfaces for recognition. Turk, M & Pentland, A Journal of Cognitive Neuroscience, 3(1):71–86, 1991. abstract bibtex Developed a near-real-time computer system that can locate and track an S's head and then recognize the person by comparing characteristics of the face with those of known individuals. The computational approach is motivated by physiology and information theory. The approach treats the face recognition problem as a 2-dimensional recognition problem. The system functions by projecting face images onto a feature space that spans the significant variations among known face images. The significant features are known as eigenfaces because they are the eigenvectors of the set of faces. They do not necessarily correspond to features such as eyes, ears, and noses. The approach provides for the ability to learn and later recognize new faces in an unsupervised manner, and is easy to implement using a neural network architecture.
@article{turk_eigenfaces_1991,
title = {Eigenfaces for recognition},
volume = {3},
abstract = {Developed a near-real-time computer system that can locate and track an S's head and then recognize the person by comparing characteristics of the face with those of known individuals. The computational approach is motivated by physiology and information theory. The approach treats the face recognition problem as a 2-dimensional recognition problem. The system functions by projecting face images onto a feature space that spans the significant variations among known face images. The significant features are known as eigenfaces because they are the eigenvectors of the set of faces. They do not necessarily correspond to features such as eyes, ears, and noses. The approach provides for the ability to learn and later recognize new faces in an unsupervised manner, and is easy to implement using a neural network architecture.},
number = {1},
journal = {Journal of Cognitive Neuroscience},
author = {Turk, M and Pentland, A},
year = {1991},
pages = {71--86},
}
Downloads: 0
{"_id":"2XhEkPQfczzmtyd5P","bibbaseid":"turk-pentland-eigenfacesforrecognition-1991","downloads":0,"creationDate":"2016-03-16T14:38:25.945Z","title":"Eigenfaces for recognition","author_short":["Turk, M","Pentland, A"],"year":1991,"bibtype":"article","biburl":"https://bibbase.org/zotero/michaeltarr","bibdata":{"bibtype":"article","type":"article","title":"Eigenfaces for recognition","volume":"3","abstract":"Developed a near-real-time computer system that can locate and track an S's head and then recognize the person by comparing characteristics of the face with those of known individuals. The computational approach is motivated by physiology and information theory. The approach treats the face recognition problem as a 2-dimensional recognition problem. The system functions by projecting face images onto a feature space that spans the significant variations among known face images. The significant features are known as eigenfaces because they are the eigenvectors of the set of faces. They do not necessarily correspond to features such as eyes, ears, and noses. The approach provides for the ability to learn and later recognize new faces in an unsupervised manner, and is easy to implement using a neural network architecture.","number":"1","journal":"Journal of Cognitive Neuroscience","author":[{"propositions":[],"lastnames":["Turk"],"firstnames":["M"],"suffixes":[]},{"propositions":[],"lastnames":["Pentland"],"firstnames":["A"],"suffixes":[]}],"year":"1991","pages":"71–86","bibtex":"@article{turk_eigenfaces_1991,\n\ttitle = {Eigenfaces for recognition},\n\tvolume = {3},\n\tabstract = {Developed a near-real-time computer system that can locate and track an S's head and then recognize the person by comparing characteristics of the face with those of known individuals. The computational approach is motivated by physiology and information theory. The approach treats the face recognition problem as a 2-dimensional recognition problem. The system functions by projecting face images onto a feature space that spans the significant variations among known face images. The significant features are known as eigenfaces because they are the eigenvectors of the set of faces. They do not necessarily correspond to features such as eyes, ears, and noses. The approach provides for the ability to learn and later recognize new faces in an unsupervised manner, and is easy to implement using a neural network architecture.},\n\tnumber = {1},\n\tjournal = {Journal of Cognitive Neuroscience},\n\tauthor = {Turk, M and Pentland, A},\n\tyear = {1991},\n\tpages = {71--86},\n}\n\n","author_short":["Turk, M","Pentland, A"],"key":"turk_eigenfaces_1991","id":"turk_eigenfaces_1991","bibbaseid":"turk-pentland-eigenfacesforrecognition-1991","role":"author","urls":{},"metadata":{"authorlinks":{}},"downloads":0,"html":""},"search_terms":["eigenfaces","recognition","turk","pentland"],"keywords":[],"authorIDs":[],"dataSources":["dWW3j9XN4xTKk2o3d","5qXSH7BrePnXHtcrf"]}