Face Recognition using Neural Networks Seminar Report-

2016

1. INTRODUCTION

Face recognition is a very challenging research area in computer vision and pattern recognition due

to variations in facial expressions, poses and illumination. Several emerging applications, from law

enforcement to commercial tasks, demand the industry to develop efficient and automated face

recognition systems. Although, many researchers have worked on the problem of face recognition

for many years still several challenges need to be solved. Difference in illumination of the scene,

changes in pose, orientation and expression are examples of some of the issues to be dealt

carefully. Also when size of face database increases the recognition time becomes a big constraint.

Face recognition is one of the biometric methods that to have the merits of both high accuracy and

low intrusiveness. It has the accuracy of a physiological approach without being intrusive. For this

reason, the face recognition has drawn the attention of researchers in fields from security,

Psychology, and image processing, to computer vision. Many algorithms have been proposed for

face recognition, Face recognition has also proven useful in other multimedia information

processing areas. Facial recognition analyzes the characteristics of a person's face images input

through a digital video camera or online face capturing. Now days we need to maintain global

security Information, in every organization or individual wants to improve their existing security

system. Most of the people need better security system which gives complete security solution.

From time to time we hear aboutthe crimes of credit card fraud, computer break-in by hackers, or

security breaches in company, in shops, in government buildings. In most of these crimes the

criminals were taking advantage of that hacking the information from commercial or academic

access control system. The systems do not grant access by who we are, but by what we have, such

as ID cards, keys, passwords, PIN numbers. These means they are really defining us or they just

Dept of ECE 1 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

want to authenticate us. It goes without Permission of owner‟s, duplicates, or acquires these

identity means, he or she will be able to access our data or our personal property any time they

want. Recently, technology became available to allow verification of true individual identity. This

technology is based in a field called "biometrics". Biometrics is a technique for identifying people

by using a unique physiological characteristic, such as a fingerprint, eye, face, etc. or behavioural

characteristics, e.g., voice and signature etc. Biometrics is the use of computers to recognize

people, considering all of the across-individual similarities and within-individual variations.

Among the various biometric ID methods, physiological methods such as fingerprint, face, DNA

are more stable than methods in behavioural category like keystroke, voice print etc.

Dept of ECE 2 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

2.LITERATURE REVIEW

There is crucial need for high security in a world where information flows in abundance.

Biometrics has now received more attention. Patel & Yagnik [1]has recognized various face

recognition techniques like Eigen faces, fisher faces, neural network, elastic bunch method, graph

matching ,feature matching and template matching. The author has mentioned various algorithms

and you can use any of them according to our requirement and application.

Many Algorithms for implementation of face recognition are popular in face recognition all having

respective advantages and disadvantages [2]. Some improves the efficiency of face recognition,

under varying illumination and expression conditions for face images. Feature representation and

classification are two key steps for face recognition. Authors have presented novel techniques for

face recognition

In Eigen faces, Turk and Pentland applied principal component analysis to face recognition and

detection [3]. L. Sirovich and M. Kirby [4, 5] used principal component analysis to efficiently

represent pictures of faces. They argued that any face images could be approximately

reconstructed by a small collection of weights for each face and a standard face picture (eigen

picture). The advantage of using neural networks for face detection is the feasibility of training a

system to capture the complex class conditional density of face patterns[6]. The feature extraction

step may be more efficient than the linear Karhunen-Loève methods which choose a

dimensionality reducing linear projection that maximizes the scatter of all projected samples. In

graph matching, patterns are modeled as graphs and pattern recognition amounts to finding a

correspondence between the nodes of different graphs [7] This technique, match facial components

Dept of ECE 3 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

to previously designed templates using appropriate energy functional. The best match of a template

in the facial image proposed by Yuille et al [8] will yield the minimum energy, where these

algorithms require a priori template modelling, in addition to their computationa l costs, which

clearly affect their performance. A different neural approach was suggested by Feraud et al [9]

based on a Constrained Generative Model (CGM), an auto associative fully connected MLP with

three layers. Lin et al [10], propose a fully automatic face recognition system based on

probabilistic decision-based neural networks (PDBNN).

Dept of ECE 4 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

3.FACE RECOGNITION

Face recognition is an interesting and successful application of pattern recognition and image

analysis. Facial images are essential for intelligent vision-based human computer interaction. It has

many applications ranging from entertainment, Information security and biometrics. Face

processing is based on the fact that the information about a user’s identity can be extracted from

the images and the computers can act accordingly.

A facial recognition system is a computer application capable of identifying or verifying a person

from a digital image or a video frame from a video source. One of the ways to do this is by

comparing selected facial features from the image and a facial database.It is typically used

in security systems and can be compared to other biometrics such as fingerprint or eye iris

recognition systems. Recently, it has also become popular as a commercial identification and

marketing tool.

Some facial recognition algorithms identify facial features by extracting landmarks, or features,

from an image of the subject's face. For example, an algorithm may analyze the relative position,

size, and/or shape of the eyes, nose, cheekbones, and jaw. These features are then used to search

for other images with matching features. Other algorithms normalize a gallery of face images and

then compress the face data, only saving the data in the image that is useful for face recognition. A

probe image is then compared with the face data. One of the earliest successful systems is based on

template matching techniques applied to a set of salient facial features, providing a sort of

compressed face representation.

Dept of ECE 5 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

Recognition algorithms can be divided into two main approaches, geometric, which look at

distinguishing features, or photometric, which is a statistical approach that distills an image into

values and compares the values with templates to eliminate variances.Popular recognition

algorithms include principal component analysis using eigenfaces, linear discriminant

analysis, elastic bunch graph matching using the Fisherface algorithm, the hidden Markov model,

the multilinear subspace learning usingtensor representation, and the neuronal motivated dynamic

link matching.

This paper proposes a new face recognition method where local features are given as the input to

the neural network. The recognition is performed by Neural Network (NN) using Back

Propagation Networks (BPN) and Radial Basis Function (RBF) networks. First, the face region is

extracted from the image by applying various pre-processing activities. The method of locating the

face region is known as face localization. The local features such as eyes and mouth are extracted

from the face region. The distance between the eye balls and the distance between the mouth end

points are calculated using the distance calculation algorithm. Then the distance values between

the left eye and the left mouth end point, the right eye and the right mouth end point, the left eye

and the right mouth end point, the right eye and the left mouth end point are calculated. These

values are given as the inputs to the neural network. Back propagation algorithm is used for

training the values. Then the network is simulated using the features taken from the test set of

images. The simulated result is given as the input to the Radial Basis Network for the function

approximation. The output from the Radial Basis Network is considered as the recognition result.

Dept of ECE 6 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

4.WHY FACE RECOGNITION??

There are a number reasons to choose face recognition over other biometrics. This includes the

following:

1. It requires no physical interaction on behalf of the user.

2. It is accurate and allows for high enrolment and verification rates.

3. It does not require an expert to interpret the comparison result.

4. It can use your existing hardware infrastructure existing cameras and image capture devices will

work with no problems.

5. It is the only biometric that allow you to perform passive identification in a one to many

environment (eg: identifying a terrorist in a busy Airport terminal).

The face is an important part of who you are and how people identify you. Except in the case of

identical twins, the face is arguably a person's most unique physical characteristics. While humans

have the innate ability to recognize and distinguish different faces for millions of years, computers

are just now catching up. For face recognition there are two types of comparisons .the first is

verification. This is where the system compares the given individual with who that individual says

they are and gives a yes or no decision. The second is identification. This is where the system

compares the given individual to all the other individuals in the database and gives a ranked list of

matches. All identification or authentication technologies operate using the following four stages:

Dept of ECE 7 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

1. Capture: a physical or behavioral sample is captured by the system during enrollment and also

in identification or verification process.

2. Extraction: unique data is extracted from the sample and a template is created.

3. Comparison: the template is then compared with a new sample.

4. Match/non match: the system decides if the features extracted from the new sample are a match

or a non match.

Face recognition starts with a picture, attempting to find a person in the image. This can be

accomplished using several methods including movement, skin tones, or blurred human shapes.

The face recognition system locates the head and finally the eyes of the individual. A matrix is then

developed based on the characteristics of the individual’s face. The method of defining the matrix

varies according to the algorithm (the mathematical process used by the computer to perform the

comparison). This matrix is then compared to matrices that are in a database and a similarity score

is generated for each comparison.

Artificial intelligence is used to simulate human interpretation of faces. In order to increase the

accuracy and adaptability, some kind of machine learning has to be implemented.

There are essentially two methods of capture. One is video imaging and the other is thermal

imaging. Video imaging is more common as standard video cameras can be used. The precise

position and the angle of the head and the surrounding lighting conditions may affect the system

performance. The complete facial image is usually captured and a number of points on the face can

then be mapped, position of the eyes, mouth and the nostrils as a example. More advanced

Dept of ECE 8 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

technologies make 3-D map of the face which multiplies the possible measurements that can be

made.

Thermal imaging has better accuracy as it uses facial temperature variations caused by vein

structure as the distinguishing traits. As the heat pattern is emitted from the face itself without

source of external radiation these systems can capture images despite the lighting condition, even

in the dark. The drawback is high cost. They are more expensive than standard video cameras.

Face recognition technologies have been associated generally with very costly top secure

applications. Today the core technologies have evolved and the cost of equipments is going down

dramatically due to the integration and the increasing processing power. Certain applications of

face recognition technology are now cost effective, reliable and highly accurate. As a result there

are no technological or financial barriers for stepping from the pilot project to widespread

deployment.

Dept of ECE 9 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

5. NEURAL NETWORK

Neural network is a very powerful and robust classification technique which can be used for

predicting not only for the known data, but also for the unknown data. It works well for both linear

and non linear separable dataset. An Artificial Neural Network (ANN) is an information

processing paradigm that is inspired by the way biological nervous systems, such as the brain,

process information. The key element of this paradigm is the novel structure of the information

processing system. It is composed of a large number of highly interconnected processing elements

(neurons) working in unison to solve specific problems. ANNs, like people, learn by example. An

ANN is configured for a specific application, such as pattern recognition or data classification,

through a learning process. Learning in biological systems involves adjustments to the synaptic

connections that exist between the neurons. This is true of ANNs as well.

Neural networks has been used in many areas such as interpreting visual scenes, speech

recognition, face recognition, finger print recognition, iris recognition etc. An ANN is composed of

a network of artificial neurons also known as "nodes". These nodes are connected to each other,

and the strength of their connections to one another is assigned a value based on their strength:

inhibition (maximum being -1.0) or excitation (maximum being +1.0). If the value of the

Dept of ECE 10 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

connection is high, then it indicates that there is a strong connection. Within each node's design, a

transfer function is built in. There are three types of neutrons in an ANN, input nodes, hidden

nodes, and output nodes.

The input nodes take information, in the form of numeric expression. The information is presented

as activation values, where each node has given a number, if the higher the number greater the

activation. This information is then passed throughout the network. Based on the connection

strengths which are weights, inhibition or excitation, and transfer functions, the activation value is

passed from node to node. Each of the nodes sums the activation values it receives; it then

modifies the value based on its transfer function. The activation flows through the network,

through hidden layers, until it reaches the output nodes. The output nodes then reflect the

meaningful.

Fig. 5.1 Structure of Neural Network

Dept of ECE 11 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

6. FACE RECOGNITION SYSTEM

The proposed system consists of a face localizer, a feature extractor and a neural network
classifier.

6.1 BLOCK DIAGRAM OF FACE RECOGNITION SYSTEM

INPUT IMAGE FACE

↓
LOCALIZATION
FEATURE
↓
EXTRACTION

↓
NEURAL NETWORK
RECOGNIZER
↓

Dept of ECE 12 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

RECOGNITION
RESULT
Fig.6.1 Schematic diagram of face recognition system

6.2 EXPLANATION

Input image is acquired by taking photographs using the digital camera. These images are taken in

color mode and saved in JPG format. However, the proposed method is suitable for working with

any file format.

6.2.1 FACE LOCALIZATION

Face localization aims to determine the image position of a single face. This is a simplified

detection problem with the assumption than an input image consists only one face. Various pre-

processing activities are done in this phase to make the raw data into usable format. The procedure

below explains the proposed face localization technique.

1) Image Conversion: The input image is first converted into the gray-scale image. The gray-scale

image is then converted into its binary form.

2) Dilation: The dilation process removes the noise encountered in the binary image. Hence, the

dilation operation is performed on the binary image obtained. The gray-scale image is then

converted into its binary form. Then, the dilated image is mapped on to the gray scale image using

intensity calculation formula below.

Dept of ECE 13 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

Let Im denotes the intensity of mapped image Id denotes the intensity of the dilated image and Ig

denotes the intensity of the gray scale image.

Im(i,j) = Ig ( i, j ) if Id ( i , j ) = 1

0 otherwise

3) Image Cropping: The mapped image is converted into binary image and the required face region

is cropped from the binary image.

Fig. 6.2 Image conversion in Face localization phase

Fig. 6.3 Dilation in Face localization phase

Dept of ECE 14 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

Fig.6.4 Image Cropping in Face localization phase

6.2.2 FEATURE EXTRACTION

The Feature Extraction is carried out by taking the features such as eyes, mouth, nose, ears etc.

Generally, there are two methods of representation about facial features: One is that the local facial

features such as eyes, nose and mouth are located; the other is about the whole facial features as

expressing with a rectangle area containing eyes, nose and mouth. In this paper, the two features,

eyes and mouth are taken into consideration. Eyes extraction is done by forming an eye map.

Mouth extraction is done by forming a mouth map.

The proposed feature extraction algorithm is explained below.

1. Divide the localized face column wise into two equal parts.

2. For each row ‘r’ do steps 3 and 4.

3. The first black pixels encountered on either side are taken as (x1, y1) and (x2, y2) respectively.

4. Calculate the distance between those points using the formula:

Distance = Sqrt ( ( x2 – x1 )2 )+ ( ( y2 –y1 )2 )

Dept of ECE 15 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

5. From step 4, two sets of non-zero distance vales corresponding to eyes and mouth are obtained.

6. Find the maximum of the distances for each non-zero set. They represent the distance between

the eyeballs and the mouth end points.

7. Using the pixels corresponding to that maximum distance, calculate the following:

i Distance from the left eyeball to the right eyeball.

ii Distance from the left mouth end point to the right mouth end point.

iii Distance from the left eyeball to the left mouth end point.

iv Distance from the right eyeball to the right mouth end point.

v Distance from the left eyeball to the right mouth end point.

vi Distance from the right eyeball to the left mouth end point.

Dept of ECE 16 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

i
Fig.6.5 Eye map formation

Fig.6.6 Mouth map formation

Dept of ECE 17 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

Fig.6.7 Determination of distances between face components.

6.2.3 NEURAL NETWORK AS A RECOGNIZER

After extracting the features from the given face image, a recognizer is needed to recognize the

face image from the stored database. Neural network can be applied for such problems[11 ,12].

This paper proposes a recognition method, which uses two networks: Back Propagation Network

(BPN) and Radial Basis Function Network (RBF). Back propagation can train multilayer feed-

forward networks with differentiable transfer functions to perform function approximation, pattern

association, and pattern classification. The BPN is designed with one input layer, one hidden layer

and one output layer. The input layer consists of six neurons. The inputs to this network are feature

Dept of ECE 18 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

vectors derived from the feature extraction method in the previous section. The network is trained

using the samples.

The Back propagation training takes place in three stages:

a. Feed forward of input training pattern

b. Back propagation of the associated error and

c. Weight adjustment.

During feed forward, each input neuron (p1) receives an input value and broadcasts it to each

hidden neuron, which in turn computes the activation and passes it on to each output unit, which

again computes the activation to obtain the net output. During training, the net output is compared

with the target value and the appropriate error is calculated. From this, the error factor is obtained

which is used to distribute the error back to the hidden layer. The weights are updated accordingly.

In a similar manner, the error factor is calculated for units. After the error factors are obtained, the

weights are updated simultaneously. The output layer contains one neuron. The result obtained

from the output layer is given as the input to the RBF.

Dept of ECE 19 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

Fig 6.8 Radial Basis Function Network

RBF uses the gaussian function for approximation. For approximating the output of BPN, it is

connected with RBF. The Radial Basis Function neural network [13, 14] is found to be very

attractive for the engineering problems. They have a very compact topology.

 They are universal approximators.

 Their learning speed is very fast because of their locally tuned neurons.

The RBF neural network has a feed forward architecture with an input layer, a hidden layer and an

output layer. In this paper, a RBF neural network is used as a recognizer in face recognition system

and the inputs to this network are the results obtained from the BPN.

Dept of ECE 20 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

Fig. 6.9 Back Propagation Network

Fig.6.10 Combined Framework of BPN and RBF

Dept of ECE 21 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

Following are the explanations of the notations used in Fig.6.10.

p – Set of input neurons

b – Bias

b1, b2 – bias

IW – Weight between Input and hidden laters

LW – Weight between hidden and Output layers

Y- Output of BPN

Wi – Weight of vector to RBF

Dept of ECE 22 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

7. ADVANTAGES
 When an element (Artificial neuron) of the neural network fails, it can continue without

problems by their parallel nature.

 A neural network learns and does not need to be reprogrammed.

 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.

 Can be implemented in any application.

 It performs tasks that a linear program cannot.

 Face recognition is also one of the most inexpensive biometric in the market and its prices

should continue to go down.

Dept of ECE 23 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

8. DISADVANTAGES

1. Need training to operate.

2. Requires high processing time for large neural networks.

3. The architecture is different from microprocessors. Therefore it needs to be emulated.

4. Face recognition systems can’t tell the difference between identical twins.

Dept of ECE 24 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

9. RESULTS

The effectiveness of the proposed face localization method and the distance calculation algorithm

are demonstrated using MATLAB. The face database consists of 90 images. Out of 90 images, 64

images are taken for training the networks. The number of epochs versus the squared error graph is

shown below.

Then the neural networks are tested with the remaining images. The BPN network accepts 2

unknown faces and it recognizes all the known faces. The combined model of BPN+RBF

recognizes all known faces and accepts 1 unknown face (false acceptance). The time consumption

and the recognition rates are tabulated in the table given below.

Dept of ECE 25 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

Fig. 9.1 Error rate versus number of Epochs

Network Total Images Training+Testing False Acceptance Recognition

time(in sec) Rate(in %)

BPN 90 3.6549 2 99.66%
BPN + RBF 90 3.6492 1 98.88%

Table 9.1 Comparison of BPN + RBF framework over BPN

Dept of ECE 26 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

10. CONCLUSION

In this paper, a new face localization technique is proposed and a new feature extraction

algorithm is developed for human face recognition. The neural network model is used for

recognizing the frontal or nearly frontal faces and the results are tabulated. A new neural

network model combined with BPN and RBF networks is developed and the network is trained

and tested. The BPNN is not only efficient but also non linear faces can also be recognized .

From these results, it can be concluded that, recognition accuracy achieved by this method is

very high. This method can be suitably extended for moving images and the images with

varying background.

Dept of ECE 27 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

11. FUTURE SCOPE

 In defense ministry and all other important places the face technology can be deployed for

better security.

 This technology can also be used effectively in various important examinations such as

SSC, HSC, Medical, Engineering, MCA, MBA, B- Pharmacy, Nursing courses etc. The

examinee can be identified and verified using Face Recognition Technique.

Dept of ECE 28 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

 In all government and private offices this system can be deployed for identification,

verification and attendance.

 It can also be deployed in police station to identify and verify the criminals.

 It can also be deployed in vaults and lockers in banks for access control verification and

identification of authentic users.

 Present bar code system could be completely replaced with the face recognition technology

as it is a better choice for access & security since the barcode could be stolen by anybody

else.

12. REFERENCES

1. Patel, Riddhi & Yagnik, Shruti B.” A Literature Survey on Face Recognition Techniques”,

International Journal of Computer Trends and Technology (IJCTT) – vol. 5 no. 4 –.p.189-194,

2013.

2. Bedre,Jyoti S &Sapka, Shubhangi.”Comparative Study of Face Recognition Techniques: A

Review”,International Journal of Computer Applications. 2012

Dept of ECE 29 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

3. M. Turk and A. Pentland, “Eigenfaces for Recognition,” J. Cognitive Neuroscience, vol. 3, no. 1,

pp. 71-86, 1991.

4. L. Sirovich and M. Kirby, “Low-Dimensional procedure for the characterisation of human faces,”

J. Optical Soc. of Am., vol. 4, pp. 519- 524, 1987.

5. M. Kirby and L. Sirovich, “Application of the KarhunenLoève procedure for the characterisation

of human faces,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, pp. 831-835,

Dec.1990

6. Kirby, M. and L. Sirovich,” Application of the Karhunen-Loeve procedure for the characterization

of human faces”. IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, pp. 833,

Dec.1990.

7. Tibe´ rio S. Caetano, Julian J. McAuley, Student Member, IEEE, Li Cheng, Member, IEEE, Quoc

V. Le, and Alex J. Smola, “Learning Graph Matching,” IEEE Transactions on Pattern Analysis and

Machine Intelligence Vol. 31, No. 6, June 2009.

8. Yuille, D. Cohen, and P. Hallinan, “Facial feature extraction from faces using deformable

templates”, Proc. IEEE Computer Soc. Conf. On Computer Vision and Pattern Recognition, pp.

104-109, 1989.

9. Feraud, R., Bernier, O., and Collobert, D. “A constrained generative model applied to face

detection”, Neural Process. Lett., Vol.5, pp 73-81,1997.

10. Lin, S.H., Kung, S.Y., Lin, L.J, “Face recognition/detection by probabilistic decision-based neural

network”, IEEE Trans. Neural Networks, Vol. 8, pp 114-132,1997.

Dept of ECE 30 Toc H Institute of Science and technology

 Face Recognition using Neural Networks Seminar Report-
2016

11. H. A. Rowley, S. Baluja and T. Kanade, “Neural Network based Face detection”, IEEE Trans. On

Pattern Recognition and Machine Intelligence, vol 20, pp 23-28, 1998.

12. S. Lawrence, C. L. Giles, A. C. Tsoi and A. D. Back, “Face Recognition: A Convolutional Neural

Networks Approach”, IEEE Trans. on Neural Networks, Special Issue on Neural Networks and

Pattern Recognition, vol.8, pp 98-113, 1997.

13. J. Haddadnia, M. Ahmadi, K. Faez,” A Hybrid Learning RBF Neural Network for Human Face

Recognition with Pseudo Zernike Moment Invariant”, IEEE International Joint conference on

Neural Network, Honolulu, HI, May 12-17, 2002.

14. Javad Haddadnia, Majid Ahmadi, and Karim Faez, “An Efficient Method for Recognition of

Human Faces Using Higher Orders Pseudo Zernike Moment Invariant”, Proceedings of the Fifth

IEEE International Conference on Automatic Face and Gesture Recognition ,2002.

Dept of ECE 31 Toc H Institute of Science and technology