2. Determining people's identity
identification methods today are Password/PIN
Token systems (such as your driver's license).
Biometric identification systems, which use
pattern recognition techniques to identify
people using their physiological characteristics.
Fingerprints are a classic example of a biometric
Newer technologies include retina and iris
recognition.
3.
4.
5. Biometrics system for checking identity using
cameras and 3D scanners
System must to recognize picture and to do
verification.
For verification Face has about 80
characteristic parameters.
6.
7.
8. some of them are: width of nose, space
between eyes, high of eyehole, shape of the
zygomatic bone and jaw width
9. Train the neural network to recognize face
from picture
The NN will take some picture's parameters
for input and try to predict a person how has
this characteristic.
11. A program likeAbrosoft which can do face
extraction in sense to find characteristic
points.
12.
Coordinates of middle of nose, middle
points of left and right eye, mouth, middle
between eyes and points of ends of nose
width.
13.
Coordinates of middle of nose, middle
points of left and right eye, mouth, middle
between eyes and points of ends of nose
width.
Calculate the Distance of two points (x1, y1)
and (x2, y2)
14. X - value that should be normalized
Xn - normalized value
Xmin - minimum value of X
Xmax - maximum value of X
16. To teach the neural network we need training data
set.
The training data set consists of input signals assigned
The neural network is trained using supervised
learning algorithms
It uses the data to adjust the network's weights and
thresholds to minimize the error on the training set.
If the network is properly trained, it has then learned
to model the (unknown) function that relates the
input variables to the output variables, and can
subsequently be used to make predictions where the
output is not known.
18. we created one basic training set .
We normalize the original data set using a
linear scaling method.Through 5 basic steps
we explained in detail the creation, training
and testing neural networks.
We have shown that the best solution to the
problem of face recognition using Neuroph
19.
20.
21.
22. (1) PCA algorithm with Mahalanobis distance
(Alexander & Smith, 2005)
(2) Half-face based algorithm (Ramanathan
et al., 2004,
(3) Eigen-eyes based algorithm (Silva &
Rosa, 2003)