Works on: Windows 10 | Windows 8.1 | Windows 8 | Windows 7 | Windows XP | Windows 2000 | Windows 2003 | Windows 2008 | Windows Vista | Windows 2012 SHA1 Hash: 79ca1a982805e3787908f05f7f284391226932b5 Size: 307.87 KB File Format: zip
Rating: 2.434782608
out of 5
based on 23 user ratings
Downloads: 304 License: Free
FisherFaces for Face Matching is a free software by Luigi Rosa and works on Windows 10, Windows 8.1, Windows 8, Windows 7, Windows XP, Windows 2000, Windows 2003, Windows 2008, Windows Vista, Windows 2012.
You can download FisherFaces for Face Matching which is 307.87 KB in size and belongs to the software category Miscellaneous. FisherFaces for Face Matching was released on 2006-09-02 and last updated on our database on 2017-02-18 and is currently at version 1.
Thank you for downloading from SoftPaz! Your download should start any moment now. It would be great if you could rate and share:
Rate this software:
Share in your network:
FisherFaces for Face Matching Description
FisherFaces for Face Matching allows you to create and modify faces in 3D linear subspace.
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 space-if the face is a Lambertian surface without shadowing.
However, since faces are not truly Lambertian surfaces and do indeed produce self-shadowing, images will deviate from this linear subspace. Rather than explicitly modeling this deviation, we linearly project the image into a subspace in a manner which discounts those regions of the face with large deviation. Our projection method is based on Fishers Linear Discriminant and produces well separated classes in a low-dimensional subspace, even under severe variation in lighting and facial expressions.
The Eigenface technique, another method based on linearly projecting the image space to a low dimensional subspace, has similar computational requirements. Yet, extensive experimental results demonstrate that the proposed "Fisherface" method has error rates that are lower than those of the Eigenface technique for tests on the Harvard and Yale Fase Databases.
Index terms: appearance-based vision, face recognition, illumination invariance, Fishers linear discriminant, face recognition, face matching, face identification, PCA, principal components analysis, fisherfaces.
Requirements:
ï¿ Matlab Image Processing Toolbox