Transcript Face Recognition Introduction  Why we are interested in face recognition?  Passport control at terminals in airports  Participant identification in meetings  System.

Face Recognition
Introduction

Why we are interested in face recognition?
 Passport control at terminals in airports
 Participant identification in meetings
 System access control
 Scanning for criminal persons
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)
Applications


It is not fool proof – many have been fooled by
identical twins
Because of these, use of facial biometrics for
identification is often questioned.
Application


Video Surveillance (On-line or off-line)
http://www.crossmatch.com/facesnap-fotoshot.php
locates and extracts images from video footage
for identification and verification
Why is Face Recognition Hard?

Many faces of Madonna
Why is Face Recognition Hard?
Face Recognition Difficulties


Identify similar faces (inter-class similarity)
Accommodate intra-class variability due to:
head pose
 illumination conditions
 expressions
 facial accessories
 aging effects


Cartoon faces
Inter-class Similarity

Different persons may have very similar appearance
Twins
Father and son
Intra-class Variability

Faces with intra-subject variations in pose, illumination,
expression, accessories, color, occlusions, and
brightness
Sketch of a Pattern Recognition
Architecture
Example: Face Detection


Scan window over image.
Classify window as either:


Face
Non-face
Profile views

Schneiderman’s
Test set as an
example
Example: Finding skin
Non-parametric Representation of CCD

Skin has a very small range of (intensity independent)
colors, and little texture




Compute an intensity-independent color measure, check if
color is in this range, check if there is little texture (median
filter)
See this as a classifier - we can set up the tests by hand, or
learn them.
get class conditional densities (histograms), priors from data
(counting)
Classifier is
Face Detection Algorithm
Face Recognition
Face Recognition: 2-D and 3-D
Image as a Feature Vector


Consider an n-pixel image to be a point in an ndimensional space, x  R n
Each pixel value is a coordinate of x.
Nearest Neighbor Classifier


Rj is the training dataset
The match for I is R1, who is closer than R2
Comments


Sometimes called “Template Matching”
Variations on distance function
Multiple templates per class- perhaps many training
images per class.
 Expensive to compute k distances, especially when
each image is big (N dimensional).
 May not generalize well to unseen examples of class.
 Some solutions:

Bayesian classification
 Dimensionality reduction

Face Recognition Solutions

Holistic or Appearance-based Face recognition
EigenFace
 LDA


Feature-based
EigenFace
EigenFace


Use Principle Component Analysis (PCA) to
determine the most discriminating features
between images of faces.
The principal component analysis or KarhunenLoeve transform is a mathematical way of
determining that linear transformation of a
sample of points in L-dimensional space which
exhibits the properties of the sample most
clearly along the coordinate axes.
PCA

http://www.cs.otago.ac.nz/cosc453/student_tu
torials/principal_components.pdf
More New Techniques in Face
Biometrics

Facial geometry, 3D face recognition
http://wwwusers.cs.york.ac.uk/~nep/research/3Dface
/tomh/3DFaceDatabase.html
3D reconstruction
Skin pattern recognition

using the details of the skin for authentication
http://pagespersoorange.fr/fingerchip/biometrics/types/face.htm
Facial thermogram

Facial thermogram requires an (expensive)
infrared camera to detect the facial heat patterns
that are unique to every human being. Technology
Recognition Systems worked on that subject in
1996-1999. Now disappeared.
http://pagespersoorange.fr/fingerchip/biometrics/types/face.htm
Side effect of Facial thermogram


can detect lies
The image on the left shows his normal facial
thermogram, and the image on the right shows
the temperature changes when he lied.
http://pagespersoorange.fr/fingerchip/biometrics/types/face.htm
Smile recognition




Probing the characteristic pattern of muscles beneath
the skin of the face.
Analyzing how the skin around the subject's mouth
moves between the two smiles.
Tracking changes in the position of tiny wrinkles in
the skin, each just a fraction of a millimetre wide.
The data is used to produce an image of the face
overlaid with tiny arrows that indicate how different
areas of skin move during a smile.
http://pagespersoorange.fr/fingerchip/biometrics/types/face.htm
Dynamic facial features

They track the motion of certain features on the
face during a facial expression (e.g., smile) and
obtain a vector field that characterizes the
deformation of the face.
http://pagespersoorange.fr/fingerchip/biometrics/types/face.htm