blob: 252d269c7b7c58c516455271876b77b4e178076e (
plain)
1
2
|
Eigenfaces vs. fisherfaces: Recognition using class specific linear projection|http://www.dtic.mil/docs/citations/AD1015508|1997|13228|67|13084856655998519010|None|http://scholar.google.com/scholar?cites=13084856655998519010&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=13084856655998519010&hl=en&as_sdt=0,5|None|We develop a face recognition algorithm which is insensitive to large variation in lighting direction and facial expression. Taking a pattern classification approach, we consider each pixel in an image as a coordinate in a high-dimensional space. We take advantage of the observation that the images of a particular face, under varying illumination but fixed pose, lie in a 3D linear subspace of the high dimensional image spaceif the face is a Lambertian surface without shadowing. However, since faces are not truly Lambertian surfaces and do …
Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection|http://scholar.google.com/https://link.springer.com/chapter/10.1007/BFb0015522|1996|609|8|10500235270745853797|None|http://scholar.google.com/scholar?cites=10500235270745853797&as_sdt=2005&sciodt=0,5&hl=en|http://scholar.google.com/scholar?cluster=10500235270745853797&hl=en&as_sdt=0,5|None|We develop a face recognition algorithm which is insensitive to gross variation in lighting direction and facial expression. Taking a pattern classification approach, we consider each pixel in an image as a coordinate in a high-dimensional space. We take advantage of the observation that the images of a particular face under varying illumination direction lie in a 3-D linear subspace of the high dimensional feature space—if the face is a Lambertian surface without self-shadowing. However, since faces are not truly Lambertian surfaces and do …
|
