Face recognition using artificial neural network

22
Face Recognition using Artificial Neural Network PRESENTED BY:- SUMEET S. KAKANI GUIDED BY:- PROF. V. M. UMALE 1

description

 

Transcript of Face recognition using artificial neural network

Page 1: Face recognition using artificial neural network

1

Face Recognition using Artificial Neural Network

PRESENTED BY:-

SUMEET S. KAKANI

GUIDED BY:-

PROF. V. M. UMALE

Page 2: Face recognition using artificial neural network

2

CONTENTS:

Introduction What is an Artificial Neural Network? ANN Structure System Overview Local image sampling The Self Organizing-Map Perceptron learning rule Convolutional Network System details Implementation Applications Conclusion References

Page 3: Face recognition using artificial neural network

3

Introduction1. Why face recognition?

Face Recognition systems enhance security, provide secure

access control, and protect personal privacy

Improvement in the performance and reliability of face

recognition

No need to remember any passwords or carry any ID

2. Why neural network?

Adaptive learning: An ability to learn how to do tasks

Self-Organization: An ANN can create its own organisation

Remarkable ability to derive meaning from complicated or

imprecise data

Page 4: Face recognition using artificial neural network

4

What is an Artificial Neural Network?

Definition: A Computing system made of a number of simple,

highly interconnected processing elements, which process

information by their dynamic state response to external input.

Motivated right from its inception by the recognition.

A machine that is designed to model the way in which the brain

performs a particular task.

A massively parallel distributed processor.

Resembles the brain in two respects:

1. Knowledge is acquired through a learning process.

2. Synaptic weights, are used to store the acquired knowledge.

Page 5: Face recognition using artificial neural network

5

ANN Structure:

A Layer with n inputs xi.

correspondent weights Wji (i=1, 2, 3...n)

The function ∑ sums the n weighted inputs and

passes the result through a non-linear function

φ(•), called the activation function.

The function φ (•) processes the adding results

plus a threshold value θ, thus producing the output

Y.

Page 6: Face recognition using artificial neural network

6

Cont…a) Processing units Receive input The adjustment of the weights

Three types of units: 1. input units 2. hidden units 3. output units During operation, units can be updated either synchronously or

asynchronously.

b) Connections between units

n Y(t) = φ( ∑ wij(t) Xj(t) + θ)

j=1c) Transfer Function: The behavior of an ANN depends on both the weights and the transfer

function that is specified for the units. This function typically falls into one of two categories:

Linear : the output activity is proportional to the total weighted output.

Threshold: the output is set at one of two levels, depending on whether the total input is greater than or less than some threshold value.

Page 7: Face recognition using artificial neural network

7

System Overview

Following are the basic processes that are used by the system to capture and compare images:

1. Detection:Recognition software searches the field of view of a video camera for faces.Once the face is in view, it is detected within a fraction of a second.

2. Alignment: Once a face is detected, the head's position, size and poseis the first thing that is determined.

3. Normalization: The image of the head is scaled and rotated so that it can be registered and mapped into an appropriate size and pose.

Page 8: Face recognition using artificial neural network

8

Cont..4. Representation:

Translation of facial data into unique code is done by the system.

5. Matching:The newly acquired facial data is compared to the stored data and (ideally) linked to at least one stored facial representationThis includes-Local image samplingThe Self Organizing-MapConvolutional Network

Page 9: Face recognition using artificial neural network

9

Local image sampling

Figure : A representation of the local image sampling process.

• We have evaluated two different methods of representing local image samples.

• In each method a window is scanned over the image as shown in figure.

Page 10: Face recognition using artificial neural network

10

The Self Organizing-Map Used to reduce the dimensions of the image vector

Self-Organizing Map(SOM), is an unsupervised learning process, which learns the distribution of a set of patterns without any class information.

Unsupervised learning: a) No external teacher and is based upon only local information.b) It is also referred to as self-organization unsupervised learning.

The basic SOM consists of:I) A 2 dimensional lattice L of neurons.II) Each neuron ni belongs to L has an associated codebook vector μi belongs to Rn.III) The lattice is either rectangular or hexagonal as shown in figure

Page 11: Face recognition using artificial neural network

11

Cont..

Figure: Rectangular and hexagonal lattice

• Self-organizing maps learn both the distribution and topology of the input vectors they are trained on.

• Here a self-organizing feature map network identifies a winning neuron i using the same procedure as employed by a competitive layer.

• However, instead of updating only the winning neuron, all neurons within a certain neighborhood of the winning neuron are updated

Page 12: Face recognition using artificial neural network

12

Perceptron learning rule

Perceptrons are trained on examples ofdesired behavior.

The desired behavior can be summarized by a set of input, output pairs as:p1t1, p2t2,………….. pQtQ

Where p is an input to the network and t is the corresponding correct (target) output.

The perceptron learning rule can be written more succinctly in terms of the errore = t - a, and the change to be made to the weight vector Δw:

Case 1: If e = 0, then make a change Δw equal to 0.

Case 2: If e = 1, then make a change Δw equal to p T.

Case 3: If e = -1, then make a change Δw equal to -p T.

Page 13: Face recognition using artificial neural network

13

Convolutional Network

Figure : A typical convolutional network.

Page 14: Face recognition using artificial neural network

14

Cont..

Automatically synthesize simple problem specific feature extractor from training data.

Feature detectors applied everywhere.

Features get progressively more global and invariant.

The whole system is trained “end-to-end” with gradient based method to minimize a global loss function.

Integrate segmentation, feature extraction, and invariant classification in one stretch.

Page 15: Face recognition using artificial neural network

15

Cont..

1. Convolutional Mechanism Capable of extracting similar features in different

places in the image. Shifting the input only shifts the feature map (robust

to shift).

2. Subsampling Mechanism The exact positions of the extracted features are

not important. Only relative position of a feature to another

feature is relevant. Reduce spatial resolution – Reduce sensitivity to

shift and distortion.

Page 16: Face recognition using artificial neural network

16

System details

For the images in the training set, a fixed size

window is stepped over the entire image.

As shown in earlier figure and local image samples

are extracted at each step.

A self-organizing map is trained on the vectors from

the previous stage

Page 17: Face recognition using artificial neural network

17

Cont..

The same window as in the first step is stepped over

all of the images in the training and test sets.

The local image samples are passed through the SOM

at each step, thereby creating new training and test

sets in the output space created by the self-

organizing map.

A convolutional neural network is trained on the

newly created training set

Page 18: Face recognition using artificial neural network

18

ImplementationTraining:

Testing:

Page 19: Face recognition using artificial neural network

19

Applications Law Enforcement: Minimizing victim trauma by narrowing mug

shot searches, Verifying identify for court records, and comparing school Surveillance camera Images to known child molesters.

Security/Counter terrorism: Access control, comparing surveillance images to Known terrorists.

   Day Care: Verify identity of individuals picking up the children.

Missing Children/Runaways Search surveillance images and the internet

for missing children and runaways.

Residential Security: Alert homeowners of approaching personnel.

Healthcare: Minimize fraud by verifying identity. Banking: Minimize fraud by verifying identity.

Page 20: Face recognition using artificial neural network

20

Conclusion

There are no explicit three-dimensional models in our system, however we have found that the quantized local image samples used as input to the convolutional network represent smoothly changing shading patterns.

Higher level features are constructed from these building blocks in successive layers of the convolutional network.

In comparison with the eigenfaces approach, we believe that the system presented here is able to learn more appropriate features in order to provide improved generalization.

Page 21: Face recognition using artificial neural network

21

References:

 1. Steve Lawrence, C. Lee Giles , “Face Recognition: A Convolutional Neural

Network Approach”, IEEE transaction, St. Lucia, Australia.

2. David a brown, Ian craw, Julian lewthwaite, “Interactive Face retrieval using self organizing maps-A SOM based approach to skin detection with application in real time systems”, IEEE 2008 conference, Berlin, Germany.

3. Shahrin Azuan Nazeer, Nazaruddin Omar' and Marzuki Khalid, “Face Recognition System using Artificial Neural Networks Approach”, IEEE - ICSCN 2007, MIT Campus, Anna University, Chennai, India. Feb. 22-24, 2007. pp.420-425.

4. M. Prakash and M. Narasimha Murty, “Recognition Methods and Their Neural- Network Models”, IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 8, NO. 1, JANUARY 2005.

5. E. Oja, “Neural networks, principal components and subspaces”, Int. J. Neural Syst., vol. 1, pp. 61–68, 2004.

Page 22: Face recognition using artificial neural network

22

THANK YOU