Face Detection and Recognition 2019

Face Recognition:
An Introduction
Face
Face Recognition
• Face is the most common biometric used by humans
• Applications range from static, mug-shot verification to
a dynamic, uncontrolled face identification in a cluttered
background
• Challenges:
• automatically locate the face
• recognize the face from a general view point under
different illumination conditions, facial expressions,
and aging effects
Authentication vs Identification
• Face Authentication/Verification (1:1 matching)
• Face Identification/Recognition (1:N matching)

Face Recognition (after detection)
• Eigenfaces: the idea
• Eigenvectors and Eigenvalues
• Co-variance
• Learning Eigenfaces from training sets of faces
• Recognition and reconstruction

Eigenfaces: the idea
• Think of a face as being a weighted combination of
some “component” or “basis” faces
• These basis faces are called eigenfaces
-8029 2900 1751 1445 4238 6193
…
Eigenfaces: representing faces
• These basis faces can be differently weighted to represent any
face
• So we can use different vectors of weights to represent different
faces
-8029 -1183 2900 -2088 1751 -4336 1445 -669 4238 -4221 6193 10549
Learning Eigenfaces
Q: How do we pick the set of basis faces?
A: We take a set of real training faces
…
❖Then we find (learn) a set of basis faces which
best represent the differences between them
❖We’ll use a statistical criterion for measuring this
notion of “best representation of the differences
between the training faces”
❖We can then store each face as a set of weights
for those basis faces
Using Eigenfaces: recognition & reconstruction
• We can use the eigenfaces in two ways

• 1: we can store and then reconstruct a face
from a set of weights
• 2: we can recognise a new picture of a familiar face

Learning Eigenfaces
• How do we learn them?

• We use a method called Principle
Components Analysis (PCA)
• To understand this we will need to
understand
– What an eigenvector is
– What covariance is
• But first we will look at what is happening
in PCA qualitatively
Eigenvectors
• An eigenvector is a vector v that obeys the following rule:
Av =  v
Where A 
is a matrix, is a scalar (called the eigenvalue)
 2 3 3
e.g. A =   one eigenvector of A is  =   since
 2 1 2
 2 3  3 12  3
 2 1  2  =  8  = 4   2 
      
so for this eigenvector of this matrix the eigenvalue is 4
Av
v
Eigenvectors
• We can think of matrices as performing
transformations on vectors (e.g rotations, reflections)
• We can think of the eigenvectors of a matrix as being
special vectors (for that matrix) that are scaled by
that matrix
• Different matrices have different eigenvectors
• Only square matrices have eigenvectors
• Not all square matrices have eigenvectors
• An n by n matrix has at most n distinct eigenvectors
• All the distinct eigenvectors of a matrix are
orthogonal (ie perpendicular)
Covariance
• Which single vector can be used to separate

these points as much as possible?
x2
x1
• This vector turns out to be a vector expressing
the direction of the correlation
• Here I have two variables x1 and x2
• They co-vary (y tends to change in roughly the
same direction as x)
Covariance
• The covariances can be expressed as a
matrix x x 1 2
x2
.617 .615  x1
C= 
.615 .717  x2
x1
• The diagonal elements are the variances
e.g. Var(x1) n
 1 1 2 −x2 )
( x i
− x )( x i
cov( x1 , x2 ) = i =1
n −1
• The covariance of two variables is:
Eigenvectors of the covariance matrix
• The covariance matrix has eigenvectors
covariance matrix .617 .615 

C=  x2
.615 .717 
eigenvectors x1
 −.735 .678
1 =   2 = 
 .678  .735
 
eigenvalues  = 0.049
1  = 1.284
2
• Eigenvectors with larger eigenvectors correspond to

directions in which the data varies more
• Finding the eigenvectors and eigenvalues of the
covariance matrix for a set of data is termed
principle components analysis
Expressing points using eigenvectors
• Suppose you think of your eigenvectors as
specifying a new vector space
• i.e. I can reference any point in terms of those

eigenvectors
• A point’s position in this new coordinate system is
what we earlier referred to as its “weight vector”
• For many data sets you can cope with fewer
dimensions in the new space than in the old space
Eigenfaces
• All we are doing in the face case is
treating the face as a point in a high-
dimensional space, and then treating the
training set of face pictures as our set of
points
• To train:
– We calculate the covariance matrix of the
faces
– We then find the eigenvectors of that
covariance matrix
• These eigenvectors are the eigenfaces or
basis faces
Eigenfaces: image space to
face space
• When we see an image of a face we can transform it to face
space
w k = x . vk
i
• There are k=1…n eigenfaces v k

• The ith face in image space is a vector x i
• The corresponding weight is wk
• We calculate the corresponding weight for every eigenface
Recognition in face space
• Recognition is now simple. We find the euclidean
distance d between our face and all the other stored
faces in face space:
2
( i i )
n
d ( w1 , w2 ) = w1
− w 2
i =1
• The closest face in face space is the chosen match

Reconstruction
• The more eigenfaces you have the better the reconstruction, but you can
have high quality reconstruction even with a small number of eigenfaces
82 70 50
30 20 10

Face Detection and Recognition 2019

Uploaded by

Copyright:

Available Formats

Face Detection and Recognition 2019

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Face Detection and Recognition 2019

Uploaded by

Copyright:

Available Formats

Face Recognition:

• Face Identification/Recognition (1:N matching)

• Eigenfaces: the idea

• Eigenvectors and Eigenvalues

• Learning Eigenfaces from training sets of faces

• Recognition and reconstruction

-8029 2900 1751 1445 4238 6193

• We can use the eigenfaces in two ways

• 2: we can recognise a new picture of a familiar face

• How do we learn them?

• Which single vector can be used to separate

covariance matrix .617 .615 

• Eigenvectors with larger eigenvectors correspond to

• i.e. I can reference any point in terms of those

• There are k=1…n eigenfaces v k

• The closest face in face space is the chosen match

You might also like