3. FACE RECOGNITION
ā¢ Face recognition involves comparing an
image with a database of stored faces in
order to identify the individual in that input
image.
ā¢ Used in human-machine
interfaces, automatic access control
system.
4. NEURAL NETWORK
ā¢ It is a system of programs and data structures that
approximates the operation of the human brain.
6. Pre-Processing
ā¢ To reduce or eliminate some of the
variations in face due to illumination.
ā¢ It normalize and enhance the face image
to improve the recognition performance.
ā¢ By using the normalization process system
robustness against scaling, posture, facial
expression and illumination is increased.
7. PRINCIPLE COMPONENT
ANALYSIS(PCA)
ā¢ It involves a mathematical procedure that
transforms a number of possibly correlated
variables into a smaller number of
uncorrelated variables called principal
components.
9. PCA Algorithm
ā¢ Step 2: Compute the expected contribution of
each sub-pattern
ā Generate the Mean and Median faces for each
person, and use these āvirtual facesā as the probe
set in training
ā Use the raw face-image sub-patterns as the
gallery set in for training, and compute the PCAās
projection matrix on these gallery set
ā For each sample in the probe set, compute its
similarity to the samples in corresponding gallery
set
10. PCA Algorithm
ā If a sample from a sub-patternās probe set is
correctly classified, the contribution of this sub-
pattern is added by 1
Face images from AR face database, and the computed
contribution matrix
11. PCA Algorithm
ā¢ Step 3: Classification
When an unknown face image comes in
ā¢ partition it into sub-patterns
ā¢ classify the unknown sampleās identity in each
sub-pattern
ā¢ Incorporate the expected contribution and the
classification result of all sub-patterns to
generate the final classification result
12. BACK-PROPAGATION
NEURAL NETWORK(BPNN)
ļIt trains the network to achieve a balance
between the ability to respond correctly to
the input patterns that are used for training
& the ability to provide good response to
the input that are similar.
ļ It requires a dataset of the desired output
for many input, making up the training set.
ļThese are necessarily Multilayer
Perceptrons(MLPs).
14. Advantages
ā¢ When an element (Artificial neuron) of the
neural network fails, it can continue without
any problem by their parallel nature.
ā¢ A neural network learns and does not need to
be reprogrammed.
ā¢ If there is plenty of data and the problem is
poorly understood to derive an approximate
model, then neural network technology is a
good choice.
15. CONCLUSION
ā¢ Face recognition can be applied in
Security measure at Air ports, Passport
verification, Criminals list verification in
police department, Visa processing ,
Verification of Electoral identification and
Card Security measure at ATMās.
Face recognition is a challengngprob as it involves identifyng the image in ol types of environ lyk-in diff facial expression,diff lighting cond,facialaccessories,aging effects.
In our body neurons have the abilities to remember, think and apply previous experiences to our every action.synapses are the receieving or input units to which input are given.the summing unit computes the inner product between inputs and synapseās weights(net inputs). After the summing unit there is a threshold that increases or reduces the net input. Then an activation function, f(I), that reduces the output variance of a neuron by mapping the thresholded net input generally within the interval [0; 1] or [-1; 1] after which we get the output.
It is abb of backward propagation of errors.it is a method of training artificial neural networks.ex-a child learns to identify a dog from ex of dogs.
The signal is generated in the input layer,propagated through the hidden layers until it reaches the output layer.