18-04-2011, 04:48 PM
PRESENTED BY-
CHINTAN HARANIA
HARSHAL RAJGOR
ISHANI PARIKH
NEHA KHIMANI
[attachment=12327]
What is Biometrics ?
A biometric is a unique, measurable characteristics of a human being that can be used to automatically recognize an individual or verify an individuals identity.
Biometrics can measure Physiological and Behavioral characteristics
a. Physiological characteristics- Finger-scan, Iris scan , Hand scan, Retina scan.
b. Behavioral characteristics- Voice , Signature, and Keystroke scan.
Why Face Recognition Technology ?
Requires no physical interaction on behalf of the user.
It is accurate and allows for high enrollment and verification rates.
It does not require any expert to interpret the comparison result.
It uses existing hardware infrastructure devices.
The only biometric which allow to perform passive identification in one to many environments.
Face Detection algorithm using Colour and Geometric Information
Feature extraction
Template matching
Difficulties in face recognition
• Text is restricted to a limited number of characters.
• The content of images is inherently different and more complicated to deal with.
• Facial expressions.
• Cosmetics
• Ageing
• Lighting
Solution
• Acquire images of faces
• Store pixel data in arrays to obtain a face database
• Obtain test image
• Store pixel data as array
• Subtract test array from database arrays
• If result is a zero matrix then match is found
EXISTING FACE RECOGNITION METHODS
Linear Discriminant Analysis
Elastic Branch Group Matching
Neural Networks
PCA (Eigenfaces)
LDA
Linear Discriminant Analysis predicts a categorical variable based on one or more metric independent variables.
Linear Discriminant Analysis (LDA)
Example
Graph Interpretation
Graphical Representation ctd.
A 100% Accurate Discriminate Analysis
Test results of LDA
Test results of a subspace LDA-based face recognition method in 1999.
E.B.G.M.
Neural network technology
Face Recognition By Principal Component Analysis (PCA)
• PCA involves a mathematical procedure that transforms a number of (possibly) correlated variables into a (smaller) number of uncorrelated variables called principal components.
• A statistical method for reducing the dimensionality of a data.
Block Diagram of PCA Based Face Recognition System
Original Image & Results Of Several Steps In Normalization Module
Recognition Process
Steps For Recognition Procedure
• Collect a set of face images (Training Set).
• Calculate the Covariance matrix, and find its eigen values and eigenvectors.
• Select the desire eigen faces.
• For each new face, project it onto the face space, and find the distance to all the known face classes.
• If the person is recognized, the new face may enter the database as this person.
• If the face was not recognized, it may enter the database as new face class.
Advantages Of Face Recognition:
• Convenience & social acceptability.
• Can be performed secretly.
• Most inexpensive biometric.
• Easy to use.
Disadvantages Of Face Recognition:
• Can’t tell the difference between Identical twins.
• Performance degradation is due to poor lighting, sunglasses, long hair or other objects partially covering the subject’s face.
• Low resolution images because of data compression.
• Less effective if facial expressions vary.
• Problem of data collection update because of change of age.
APPLICATIONS OF FACE RECOGNITION
BIOMETRICS – driver’s licenses, entitlement programs, immigration, national ID, passports, voter registration
INFORMATION SECURITY – application security, desktop logon (windows NT, windows 95), database security, file encryption, intranet security, internet access, medical records, official company records, national records
LAW ENFORCEMENT AND SURVEILLANCE – advanced video surveillance, CCTV control portal, post-event analysis
SMART CARDS – stored value security, user authentication
ACCESS CONTROL – facility access, vehicular access
CONCLUSION
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 intergration 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.