PRESENTED BY:
SUNIL.K.DASAR

---

[attachment=11199]
Biometric Person Identification
Abstract
Conventional method of identification based on possession of id cards or exclusive knowledge like a social security number or a password are not altogether reliable. Id cards can be lost, forged, or misplaced; passwords can be forgotten or compromised.
Rather than using a password to identify yourself to a computer, why not use physical characteristic such as your voice, face or fingerprint? Such bodily measures, known as biometrics, have the appeal that they cannot be lost, forgotten or passed from one person to another, and they are very hard to forge.
Introduction
There are a variety of means for identifying a person's identity:
• appearance (how the person looks, e.g. height, gender, weight)
• social behavior (how a person interacts with others)
• name (what the person is called)
• codes (what a person is called by an organization)
• knowledge ( what the person knows)
• possession ( what the person owns)
• natural physiology (who the person is, e.g. facial characteristics)
The goal of authentication is to protect a system against unauthorized use. This feature enables also the protection of subscribers by denying the possibility for intruders to impersonate authorized users. Authentication procedures are based on the following approaches :
• Proof by Knowledge. The verifier knows information regarding the claimed identity that can only be known or produced by a principal with that identity (e.g. passport, password, personal identification number (PIN), questionnaire).
• Proof by Possession. The claimant will be authorized by the possession of an object (e.g. magnetic card, smart card, optical card).
• Proof by Property. The claimant directly measures certain claimant properties using human characteristics (e.g. Biometrics).
Conventional method of identification based on possession of id cards or exclusive knowledge like a social security number or a password are not altogether reliable. Id cards can be lost, forged, or misplaced; passwords can be forgotten or compromised.
Rather than using a password to identify yourself to a computer, why not use physical characteristic such as your voice, face or fingerprint? Such bodily measures, known as biometrics, have the appeal that they cannot be lost, forgotten or passed from one person to another, and they are very hard to forge.
What is Biometric system?
Biometrics are automated methods of recognizing a person based on a physiological or behavioral characteristic. Among the features measured are; face fingerprints, hand geometry, handwriting, iris, retinal, vein, and voice. Biometric technologies are becoming the foundation of an extensive array of highly secure identification and personal verification solutions. As the level of security breaches and transaction fraud increases, the need for highly secure identification and personal verification technologies is becoming apparent.
Biometric-based solutions are able to provide confidential financial transactions and personal data privacy. The need for biometrics can be found in federal, state and local governments, in the military, and in commercial applications. Enterprise-wide network security infrastructures, government IDs, secure electronic banking, investing and other financial transactions, retail sales, law enforcement, and health and social services are already benefiting from these technologies.
We can categorize the biometric techniques into two classes:
• Physiological based techniques include facial analysis, fingerprint, hand geometry, retinal analysis, DNA and measure the physiological characteristics of a person.
• Behavior based techniques include signature, key stroke, voice, smell, sweat pores analysis and measure behavioral characteristics.
Biometric System
A biometric system can be divided into two stages; the enrollment module and the identification module.
Logical module of a biometric system
1. Enrollment module:
The enrollment module is responsible for training the system to identify a given person. During the enrollment stage, a biometric sensor scans the person’s physiognomy to create a digital representation to generate a more compact and expressive representation called a template.
The template for each user is stored in a biometric system database; the database can be a central or distributed database, such as the one in which each user’s template is stored on a smart card and issued to the user.
2. Identification module:
The identification module is responsible for recognizing the person. During the identification stage, the biometric sensor captures the characteristic of the person to be identified and converts it into the same digital format as the template. The resulting template is fed to the feature matcher, which compares it against the stored template to determine whether the two templates match.
Different biometric systems are
1. Face recognition
2. Speech recognition
3. Finger print recognition
4. Iris recognition
5. Multimodal biometric identification
6. Signature Verification
7. Retinal Analysis
Face recognition
The premise of this approach is that face characteristics (e.g. size of nose, shape of eyes, chin, eyebrows, mouth etc) are unique revealing individuals identity. This now increasingly developed method is expensive since it is using neural network methodologies. They use cameras to extract unique facial feature data which is stored on a chip card or a magnetic stripe card. The person swipes his card to a small camera to take an image. The software application on site compares the data with the person's stored data.
Effectiveness
Operational:
In the existing facial recognition systems certain restrictions are imposed by the user e.g. he/she should be looking straight in the camera with certain light in order for the system to analyze and identify the person. However various new graph matching techniques will enhance the quality of picture decreasing the constraints.
The system will not be able to analyze people with imposed physical characteristics such as beard, hair style or with certain facial expressions.
Users find it very naturally to be identified by their face since this is the most traditional way of identification. It is highly acceptable.
Technical
Facial recognition systems are unable to cope with angles or facial expressions which are a little different from those used during the encoding process. The templates should be updated since changes occur in the facial skeleton during the human aging process
Speech Recognition
Speech is a predominantly behavioral biometrics. The invariance in the individual characteristics of human speech is primarily due to relatively invariant shape/size of the vocal tracts; mouth, nasal cavities and lips synthesizing the sound.Speech of a person are distinctive but may not contain sufficient invariant information to offer large-scale recognition.
Speech-based recognition could be based on either text-dependent or text-independent speech input. A text-dependent verification authenticates the identity of an individual based on the utterance of a fixed predetermined phrase. A text-independent verification verifies the identity of a speaker independent of the phrase, which is difficult than the text-dependent verification but offers more protection against fraud.
However, Speech based feature are sensitive to a number of factors such as background noise as well as the emotional and physical state of the speaker. Speech-based authentication is currently restricted to low-security applications because of high variability in an individual’s voice and poor accuracy performance of a typical speech-based authentication system.