You are on page 1of 11

ECWAY TECHNOLOGIES

IEEE SOFTWARE | EMBEDDED | MECHANICAL | ROBOTICS PROJECTS DEVELOPMENT

Visit: www.ecwaytechnologies.com | www.ecwayprojects.com
ecwaytechnologies@gmail.com

Mail to:

FACE RECOGNITION USING ARTIFICIAL NEURAL NETWORKS

ABSTRACT:
Face recognition is done naturally by humans. However, developing a computer algorithm to do
the same thing is difficult. Assume for the moment we start with images, and we want to
distinguish between images of different people. One class of methods presupposes the existence
of certain features in the image, i.e. eyes, nose, mouth, hair, and an algorithm are devised to find
and characterize these features. Face recognition is an important research problem spanning
numerous fields and disciplines. This because face recognition, in additional to having numerous
practical applications such as bankcard identification, access control, Mug shots searching,
security monitoring, and surveillance system, is a fundamental human behavior that is essential
for effective communications and interactions among people.
Face recognition is one of biometric methods, to identify given face image using main features of
face. In this paper, a neural based algorithm is presented, to detect frontal views of faces. The
dimensionality of face image is reduced by the Principal component analysis (PCA) and the
recognition is done by the Back propagation Neural Network (BPNN) successful face
recognition methodology depends heavily on the particular choice of the features used by the
pattern classifier. The Back-Propagation is the best known and widely used learning algorithm in
training multilayer perceptrons (MLP).
The MLP refer to the network consisting of a set of sensory units (source nodes) that constitute
the input layer, one or more hidden layers of computation nodes, and an output layer of
computation nodes. The input signal propagates through the network in a forward direction, from
left to right and on a layer-by-layer basis. Back propagation is a multi-layer feed forward,
supervised learning network based on gradient descent learning rule. This BPNN provides a
computationally efficient method for changing the weights in feed forward network, with
differentiable activation function units, to learn a training set of input-output data.

OUR OFFICES @ CHENNAI / TRICHY / KARUR / ERODE / MADURAI / SALEM / COIMBATORE /

CELL: +91 9894917187 | 875487
1111 / 2111 / 3111 / 4111 / 5111 / 6111

BANGALORE / HYDRABAD

the need for higher accuracy system remains. Criminals list verification in police department. Visa processing . raising the bar for face recognition system. growth and progress will continue. Through the determination and commitment of industry.ecwayprojects. thus avoiding security hassles.com | www. and organized standards bodies. government evolutions. however. OUR OFFICES @ CHENNAI / TRICHY / KARUR / ERODE / MADURAI / SALEM / COIMBATORE / CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111 BANGALORE / HYDRABAD . face recognition is used to identify a person on the spot and grant access to a building or a compound. Computer based face recognition system is very useful for the police. The computer based face recognition industry has made much useful advancement in the past decade. Passport verification.ecwaytechnologies. and for government for various security regions. Face recognition can be applied in Security measure at Air ports.com ecwaytechnologies@gmail. Verification of Electoral identification and Card Security measure at ATM’s.com Mail to: SCOPE OF THE PROJECT: Real time face recognition: Here. industries.ECWAY TECHNOLOGIES IEEE SOFTWARE | EMBEDDED | MECHANICAL | ROBOTICS PROJECTS DEVELOPMENT Visit: www. In this case the face is compared against a multiple training samples of a person.

Therefore. canbe important. despite of large changes in the visual stimulus due to viewing conditions. can outperform super computers. A child can accurately identify a face. playing a major role in conveying identity and emotion. Although it is clear that people are good at face recognition. multi-dimensional visual stimuli. but recently the recognition process has now matured into a science of sophisticated mathematical representations and matching processes. expression. Developing a computational model of face recognition is quite difficult. Even the ability to merely detect faces.ECWAY TECHNOLOGIES IEEE SOFTWARE | EMBEDDED | MECHANICAL | ROBOTICS PROJECTS DEVELOPMENT Visit: www. and distractions such as glasses. adaptive nature. the main idea is to engineer a system which can emulate what a child can do. This skill is quite robust. but for a computer it is a cumbersome task.com ecwaytechnologies@gmail. credit card verification. The human brain has numerous highly interconnected biological neurons which. criminal identification etc. Face recognition has become an important issue in many applications such as security systems. OUR OFFICES @ CHENNAI / TRICHY / KARUR / ERODE / MADURAI / SALEM / COIMBATORE / CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111 BANGALORE / HYDRABAD . Early face recognition algorithms used simple geometric models. it is not at all obvious how faces are encoded or decoded by a human brain. A human can recognize thousands of faces learned throughout the lifetime and identify familiar faces at a glance even after years of separation.ecwaytechnologies. learning skills and generalization capabilities of the nervous system.com Mail to: INTRODUCTION: Human beings have recognition capabilities that are unparalleled in the modern computing era. These are mainly due to the high degree of interconnectivity. on some specific tasks. The face is the primary focus of attention in the society. Advancements in computing capability over the past few decades have enabled comparable recognition capabilities from such engineered systems quite successfully. Human face recognition has been studied for more than twenty years. Although the ability to infer intelligence or character from facial appearance is suspect.com | www. Major advancements and initiatives have propelled face recognition technology into the spotlight. beards or changes in hair style. the human ability to recognize faces is remarkable. as opposed to recognizing them. aging. because faces are complex.ecwayprojects.

In this method. in which many early vision techniques can be involved.ECWAY TECHNOLOGIES IEEE SOFTWARE | EMBEDDED | MECHANICAL | ROBOTICS PROJECTS DEVELOPMENT Visit: www. Further Artificial Neural Network was used for classification. For face identification the starting step involves extraction of the relevant features from facial images. with the help of deformable templates and extensive mathematics. information that best describes a face is derived from the entire face image in pattern recognition have shown that any particular face can be represented in terms of a best coordinate system termed as "eigenfaces" proposed a face recognition method based on the eigenfaces approach. Neural Network concept is used because of its ability to learn ' from observed data. principal component analysis method. OUR OFFICES @ CHENNAI / TRICHY / KARUR / ERODE / MADURAI / SALEM / COIMBATORE / CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111 BANGALORE / HYDRABAD .ecwaytechnologies. Principal Component analysis for face recognition is based on the information theory approach in which the relevant information in a face image is extracted as efficiently as possible. Then key information from the basic parts of face is gathered and converted into a feature vector used deformable templates in contour extraction of face images. given a set of features. The first method is based on extracting feature vectors from the basic parts of a face such as eyes. Another method is based on the information theory concepts viz. face recognition is a very high level computer vision task. nose.com Mail to: Therefore. A big challenge is how to quantize facial features so that a computer is able to recognize a face.com ecwaytechnologies@gmail. and chin. Investigations by numerous researchers over the past several years indicate that certain facial characteristics are used by human beings to identify faces.com | www. mouth. PCA and ANN. An unsupervised pattern recognition scheme is proposed in this paper which is independent of excessive geometry and computation. There are two basic methods for face recognition.ecwayprojects. Face Recognition system is implemented based on eigenface.

com | www.com ecwaytechnologies@gmail.ecwaytechnologies.ECWAY TECHNOLOGIES IEEE SOFTWARE | EMBEDDED | MECHANICAL | ROBOTICS PROJECTS DEVELOPMENT Visit: www.com Mail to: EXISTING SYSTEM: DISADVANTAGES: OUR OFFICES @ CHENNAI / TRICHY / KARUR / ERODE / MADURAI / SALEM / COIMBATORE / CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111 BANGALORE / HYDRABAD .ecwayprojects.

non linear face images can be recognized easily. emphasizing the significant local and global features. with and without Glasses). the relevant information in a face image is extracted. PCA and ANN.ecwaytechnologies. declare a match etc. In this case. The proposed technique is coding and decoding of face images. The proposed method is independent of any judgment of features (open/closed eyes.for the face recognition we have need some steps apply like acquiring a sample. the intervention of a human operator will be required in order to select the best fit from the candidate list.com | www. different facial expressions. In the language of information theory. Hence it is concluded that this method has the acceptance ratio is more than 90 % and execution time of only few seconds. We proposed in this paper which is independent of excessive geometry and computation. Neural Network concept is used because of its ability to learn ' from observed data.com Mail to: PROPOSED SYSTEM: We proposed neural networks face recognition using Eigen faces has been shown to be accurate and fast.ECWAY TECHNOLOGIES IEEE SOFTWARE | EMBEDDED | MECHANICAL | ROBOTICS PROJECTS DEVELOPMENT Visit: www.com ecwaytechnologies@gmail. encoded and then compared with a database of models. Face recognition process:. compression template. When BPNN technique is combined with PCA.ecwayprojects. Recognition system is implemented based on eigenface. extracting feature. Further Artificial Neural Network was used for classification. OUR OFFICES @ CHENNAI / TRICHY / KARUR / ERODE / MADURAI / SALEM / COIMBATORE / CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111 BANGALORE / HYDRABAD . Principal component analysis for face recognition is based on the information theory approach in which the relevant information in a face image is extracted as efficiently as possible. The face recognition system will return a candidate match list of potential matches.

Here learning process in Back propagation requires pairs of input and target vectors.  Back propagation is a multi-layer feed forward.ECWAY TECHNOLOGIES IEEE SOFTWARE | EMBEDDED | MECHANICAL | ROBOTICS PROJECTS DEVELOPMENT Visit: www.  A Generalized Neural Network stimulation is applied to the inputs of the first layer.com ecwaytechnologies@gmail. Each link between neurons has a unique weighting value.com | www. and signals propagate through the middle (hidden) layer's) to the output layer. This BPNN provides a computationally efficient method for changing the weights in feed forward network.com Mail to: ADVANTAGES:  A successful face recognition methodology depends heavily on the particular choice of the features used by the pattern classifier .ecwaytechnologies. OUR OFFICES @ CHENNAI / TRICHY / KARUR / ERODE / MADURAI / SALEM / COIMBATORE / CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111 BANGALORE / HYDRABAD .  A typical back propagation network with Multi-layer. supervised learning network based on gradient descent learning rule. The output vector ‘o‘is compared with target vector’t’.The Back-Propagation is the best known and widely used learning algorithm in training multilayer perceptions.ecwayprojects. feed-forward supervised learning is as shown in the figure.

1.ECWAY TECHNOLOGIES IEEE SOFTWARE | EMBEDDED | MECHANICAL | ROBOTICS PROJECTS DEVELOPMENT Visit: www.ecwayprojects.20 GB .com ecwaytechnologies@gmail.com Mail to: HARDWARE & SOFTWARE REQUIREMENTS: HARDWARE REQUIREMENT:  Processor        - Speed RAM Hard Disk Floppy Drive Key Board Mouse Monitor Pentium –IV .44 MB .SVGA SOFTWARE REQUIREMENTS:  Operating System : Windows XP or Win7  Front End : MATLAB  Document : MS-Office 2007 OUR OFFICES @ CHENNAI / TRICHY / KARUR / ERODE / MADURAI / SALEM / COIMBATORE / CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111 BANGALORE / HYDRABAD .ecwaytechnologies.1.Two or Three Button Mouse .com | www.1 GHz .Standard Windows Keyboard .256 MB (min) .

ecwayprojects.ecwaytechnologies.ECWAY TECHNOLOGIES IEEE SOFTWARE | EMBEDDED | MECHANICAL | ROBOTICS PROJECTS DEVELOPMENT Visit: www.com Mail to: ARCHITECTURE DIAGRAM: OUR OFFICES @ CHENNAI / TRICHY / KARUR / ERODE / MADURAI / SALEM / COIMBATORE / CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111 BANGALORE / HYDRABAD .com | www.com ecwaytechnologies@gmail.

com ecwaytechnologies@gmail.com | www.com Mail to: MODULES: IMAGE PRE-PROCESSING: FACE DETECTION (PCA): FACE RECOGNITION (ANN): FACE IDETIFICATION: OUR OFFICES @ CHENNAI / TRICHY / KARUR / ERODE / MADURAI / SALEM / COIMBATORE / CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111 BANGALORE / HYDRABAD .ecwaytechnologies.ECWAY TECHNOLOGIES IEEE SOFTWARE | EMBEDDED | MECHANICAL | ROBOTICS PROJECTS DEVELOPMENT Visit: www.ecwayprojects.

In face recognition system. Appearance based.com Mail to: CONCLUSION AND FUTURE WORK: BPNN technique has also been successfully used for face recognition is better than the other techniques PCA for the given face database and the classifier used.com ecwaytechnologies@gmail. It is a very interesting and challenging biometric technique of identifying individuals by facial features. OUR OFFICES @ CHENNAI / TRICHY / KARUR / ERODE / MADURAI / SALEM / COIMBATORE / CELL: +91 9894917187 | 875487 1111 / 2111 / 3111 / 4111 / 5111 / 6111 BANGALORE / HYDRABAD . A recognition score for test lot is calculated by considering almost all the variants of feature extraction methods on a recognition rate of 97.ECWAY TECHNOLOGIES IEEE SOFTWARE | EMBEDDED | MECHANICAL | ROBOTICS PROJECTS DEVELOPMENT Visit: www. Proposed methodology is connection of two stages – Feature extraction using principle component analysis and recognition using the feed forward back propagation Neural Network.com | www. Face is a complex multidimensional visual model and developing a computational model for face recognition is difficult. The algorithm has been tested on more than images. feature based and texture based methods are for face recognition. rule based. Neural Networks make use of new face image and the stored face images to determine if there is a match. The paper presents a methodology for face recognition based on information theory approach of coding and decoding the face image. Whenever we get a new image. we have database of images stored in the system. it is compared with the database of images already stored in the system.ecwaytechnologies.018%.ecwayprojects.