face recognition using artificial neural network

10
Face Recognition using Artificial Neural Network Prepared by 10BIT036

Upload: mayank

Post on 06-Nov-2015

29 views

Category:

Documents


0 download

DESCRIPTION

Face Recognition TechnologyArtificial Neural Network

TRANSCRIPT

Face Recognition using Artificial Neural Network

Face Recognition using Artificial Neural NetworkPrepared by 10BIT036Facial Recognition System

Face Recognition is one of the biometric methods ,to identify given face image using main feature of face.One of the ways to do this is by comparing the selected facial features from the image and a facial database.Each human face has almost 80 nodal points which are used to distinguish one person from the other.

Where it is used?Airports and Railway Stations.Government Offices.Financial Institutions.Stadiums.To access Personal Information.Business of all Kind.Voters Verification.

Stages of Identification of an ImageFour Stages of IdentificationCapture- Capture the behavioral sample.Extract - Unique data is extracted from the sample and a template is created.Comparison- The template in the database is compared with the new template.Match/Non-match- The system decides whether the new sample are matched or not.How Facial Recognition Works?

Neural Network ApproachArtificial Neural Network is an information processing paradigm that is inspired by the way biological nervous system such as brain, process information.ANN like people, learn by example. They can therefore be trained with known examples of a problem to acquire knowledge about it.ANN processes information in parallel, at high speed, and in distributed manner.ANN are robust system and are fault tolerant. They can, therefore , recall full patterns from incomplete, partial or noisy patterns.ANN exhibits mapping capabilities , i.e. they can map input patterns to their associated output patterns.

Architecture of Neural NetworksANN structure can be represented using a directed graph G(V,E) where Vertices represent Neurons and Edges represent Synaptic Link. The edges are labeled by the weights attached to the synaptic link.Feed-forward NetworksFeed-forward ANN allow signals to travel one way only ; from input to output. There is no feedback(loops). i.e. Output of any layer does not affect that same layer .Extensively used in pattern recognition.

Feedback NetworksFeedback networks can have signals travelling in both directions by introducing loops in the network. Feedback networks are very powerful and can get extremely complicated.

Network LayersANN consists of three layers of units : input, hidden ,output.The activity of the input units represents the raw information that is fed into the network.The activity of the hidden unit is determined by the activities of the input units and the weight on the connections between the input and hidden units.The behaviour of the output units depends on the activity of the hidden units and the weights between the hidden and output units.

Learning MethodsPopular learning methods are Supervised learning and Unsupervised learning.Supervised Learning:-In supervised learning ,a teacher assumed to be present during the learning process, i.e. the network aims to minimize the error between the target(desired) output presented by the teacher and the computed output, to achieve better performance.Unsupervised learning:-In unsupervised learning , there is no teacher present to hand over the desired output and the network therefore tries to learn by itself, organizing the input instances of the problem.