Linear Algebra

National University of Computer and

Emerging Sciences - FAST

Assignment No. 2

Topic: Application of Eigen Values

Dated: 10th December, 2010

Instructor: Sir Maqsood Alam

Name: Aarij Siddiqui

Id: 09-2197
Section: A
 Application of Eigen Values
Introduction:
Eigen values can be seen being implemented in many things, where magnitude increases and
direction remains constant, therefore there are many applications of Eigen Values, some of them
are listed below:

 Vibration Analysis
 Geology and glaciology
 Principal components analysis
 Tensor of Inertia
 Stress Tensor
 Eigenfaces and Eigen voices
 Eigen Values of a graph, and many more

For this Assignment I have chosen Eigenfaces.

Eigen Values Implemented in Eigen faces

Acknowledgement / References:

Eigenvalue is a very important part of linear algebra, having large number of applications.
The reason of choosing Eigenface as a topic was based on the last lecture of the course and in which
we discussed about the Principal Component Analysis and Eigenface is an example of Principal
Component Analysis.

I have taken help from wikipedia.org through google.com

Introduction:

In image processing, processed images of faces can be seen as vectors whose

components are the brightness’s of each pixel. The dimension of this vector space is the
number of pixels. The eigenvectors of the covariance matrix considered for a large set of
normalized pictures of faces are called eigenfaces. This is an example of principal components
analysis (PCA). They are very useful for expressing any face image as a linear combination of
some of them. In the facial recognition branch, eigenfaces provide a means of applying data
compression to faces for identification purposes.
Implementation:

1. Prepare a set of face images. The pictures constituting the set should be taken under the same
lighting conditions, and must have the eyes and mouths aligned in all the images. All the images
should be of same pixel resolution. Each image is treated as one vector; simply by concatenating
(the process of adding one after another) the rows of pixels in the original image, resulting in a
single row with Row × Column elements. For this implementation, it is assumed that all images
of the set are stored in a single matrix T, where each row of the matrix is an image.

2. Subtract the mean. The average image ‘A’ has to be calculated and then subtracted from each
original image in T.

3. Calculate the eigenvectors and eigenvalues of the covariance matrix S (explained in class). Each
eigenvector has the same dimensions as the original images, and thus can itself be seen as an
image. The eigenvectors of this covariance matrix are therefore called eigenfaces. They are the
directions in which the images differ from the mean image.

4. Choose the principal components. The D x D covariance matrix will result in D eigenvectors, each
representing a direction in the Row × Column-dimensional image space. The eigenvectors
(eigenfaces) with largest associated eigenvalue are kept.

5. These eigenfaces can now be used to represent both existing and new faces: we can project a
new (mean-subtracted) image on the eigenfaces and thereby record how that new face differs
from the mean face. The eigenvalues associated with each eigenface represent how much the
images in the set vary from the mean image in that direction. We lose information by projecting
the image on a subset of the eigenvectors, but we minimize this loss by keeping those
eigenfaces with the largest eigenvalues. For instance, if we are working with a 100 x 100 image,
then we will obtain 10,000 eigenvectors. In practical applications, most faces can typically be
identified using a projection on between 100 and 150 eigenfaces, so that most of the 10,000
eigenvectors can be discarded.

NOTE: The above application is similar to the one explained in class where we discussed about
computing the amount of rainfall in various regions of Pakistan through Principal Components Analysis
(PCA) by taking a pictorial data from metrological department of Pakistan. Therefore we can conclude
that Eigenface is an example or branch of Principal Component Analysis.