Facial Recognition with Neural Networks Matt Fig

advertisement
Facial Recognition
with
Neural Networks
Matt Fig
Image Processing
Fall, 2013
Introduction to Neural Networks
• Attempts to imitate human neurology
• Composed of nonlinear computational
functions called neurons
• Requires training with known data sets
• For linearly separable data sets,
convergence is guaranteed
• More complex data sets use a technique
called back propagation
Introduction Continued
• Consider two sets, each with two
points given by ω1={(0,0,1),(0,1,1)}
and ω2= {(1,0,1),(1,1,1)}
• Want to classify unknown point
• Algorithm finds “decision boundary”
between given sets
• In this case the boundary is a line
• Minimize D
D  y  w y
T
Example
• To do this we iterate according to (for some
positive constant c)
 wk  cyk if yk  1 and wTk yk  0

wk 1   wk  cyk if yk  2 and wTk yk  0

 wk 1  wk otherwise
Example

• If we choose w1   0,0,0
T
• The algorithm converges to

T
w   2,0,1
in 14 iterations.
Example Continued
• Equation of line is
D  y   2 x1  1  0  x1 
1
2
Advanced Networks
• Need something else for non-separable data sets
• Here a minimization function of this form is used
2
1
T
J  w   r  w y 
2
• r is the desired response for the particular training
vector y
• Minimizes least squared error
Advanced Networks
• Weight vector becomes
wk 1  wk    rk  wTk yk  yk
• To establish a network, create several layers
of these neurons connected such that the
output of every function in one layer is an
input into the functions in the next
Neural Network
Facial Recognition
• Many MATLAB solutions online
• One was chosen as a basis for project
• Trained with 64 random faces
Testing
• The trained network was tested for
effectiveness as a function of noise and
lighting intensity
• 5 people were used for experiments
• Gaussian noise was added with varying
intensities
• Light was adjusted 5 stops with dimmer
• As expected, more noise leads to more
misses in identification, same with lighting.
Gaussian Noise
Dimming
Re-training
• After these results, noisy and dimmed
images were added to the training set.
• This results in across the board
improvement in identification success
• For a complete and reliable system, many
more faces in many more situations
should be added to the training database
Questions?
Download