Biometrics

Unit- I Introduction: What is Biometrics, History - Types of biometric Traits - General

architecture of biometric systems - Basic working of biometric matching - Biometric system
error and performance measures - Design of biometric system - Applications of biometrics,
Biometrics versus traditional authentication methods. Face Biometrics: Introduction -
Background of Face Recognition - Design of Face Recognition System - Neural Network for
Face Recognition - Face Detection in Video Sequences - Challenges in Face Biometrics -
Face Recognition Methods - Advantages and Disadvantages.
What is Biometerics?
Biometrics is the measurement and statistical analysis of people's unique physical and
behavioral characteristics. The technology is mainly used for identification and access control
or for identifying individuals who are under surveillance.
History
The history of biometrics can be traced back to ancient times, when people used fingerprints
and handprints as seals and signatures. In the late 19th century, Alphonse Bertillon began
using biometrics for identification and security purposes. In 1963, Mitchell Trauring
published the first scientific paper on automated fingerprint matching in the journal Nature.
Father of Biometrics Alphonse Bertillon
Alphonse Bertillon, 22 April 1853 – 13 February 1914) was a French police officer and
biometrics researcher who applied the anthropological technique of anthropometry to law
enforcement creating an identification system based on physical measurements. Class on the
Bertillon system in France in 1911.
Types of biometric Traits:
General architecture of biometric systems:
Biometric System Architecture
Biometric system architecture has the following main components:

Biometric Architecture

1. Sensor: The sensor is the first block of the biometric system which collects all the
important data for biometrics. It is the interface between the system and the real world.
Typically, it is an image acquisition system, but it depends on the features or characteristics
required that it has to be replaced or not.
2. Pre-processing: It is the second block that executes all the pre-processing. Its function is
to enhance the input and to eliminate artifacts from the sensor, background noise, etc. It
performs some kind of normalization.
3. Feature extractor: This is the third and the most important step in the biometric system.
Extraction of features is to be done to identify them at a later stage. The goal of a feature
extractor is to characterize an object to be recognized by measurements.
4. Template generator: The template generator generates the templates that are used for
authentication with the help of the extracted features. A template is a vector of numbers or
an image with distinct tracts. Characteristics obtained from the source groups come together
to form a template. Templates are being stored in the database for comparison and serve as
input for the match.
5. Matcher: The matching phase is performed by the use of a match. In this part, the
procured template is given to a matcher that compares it with the stored templates using
various algorithms such as Hamming distance, etc. After matching the inputs, the results
will be generated.
6. Application device: It is a device that uses the results of a biometric system. The Iris
recognition system and facial recognition system are some common examples of
application devices.
Basic working of biometric matching:
Biometric matching is the process of comparing two biometric signatures to determine the
degree of match between them. This process is usually done in two steps: enrollment and
matching.
Enrollment
The system captures the individual's biometric traits for the first time and creates a unique
template that represents their data. This template can be based on a variety of biometric
features, such as fingerprints, veins, or facial recognition.
Matching
When a verification or authentication request is made, the system compares the newly
captured biometric data to the stored template to determine if there is a match.
The system uses mathematical models and algorithms specific to each type of biometric trait
to measure the level of similarity. The system then uses previously set parameters to establish
a tolerance range, and if the data is within that range, it is considered to be a match. The
results of each match are often represented as a score, ranging from "quite sure it is a
different person" to "almost certain it is the same person".
Biometric system error and performance measures:
Biometric system manufacturers claim high system performance which is practically difficult
to achieve in actual operating environments. The possible reasons are, tests conducted in
controlled environment setups, limitations on hardware, etc.
For example, a voice recognition system can work efficiently only in quiet environment, a
facial recognition system can work fine if lighting conditions are controlled, and candidates
can be trained to clean and place their fingers properly on the fingerprint scanners.
However, in practice, such ideal conditions may not be available in the target operating
environment.
Performance Measurements:
The performance measurements of a biometric system are closely tied to False Reject Rate
(FRR) and False Accept Rate (FAR).
FRR is also known as Type-I error or False Non Match Rate (FNMR) which states the
likelihood of a legitimate user being rejected by the system.
FAR is referred to as Type-II error or False Match Rate (FMR) which states the likelihood
of a false identity claim being accepted by the system.
An ideal biometric system is expected to produce zero value for both FAR and FRR. Means it
should accept all genuine users and reject all fake identity claims, which is practically not
achievable.
FAR and FRR are inversely proportional to each other. If FAR is improved, then the FRR
declines. A biometric system providing high FRR ensures high security. If the FRR is too
high, then the system requires to enter the live sample a number of times, which makes it less
efficient.
The performance of current biometrics technologies is far from the ideal. Hence the system
developers need to keep a good balance between these two factors depending on the security
requirements.
Design of biometric system:
The design of a biometric system involves defining its architecture, choosing the right
hardware and software, and creating an effective administration policy. The system should
meet the specified requirements, which are usually defined by six main design
parameters:accuracy, throughput, cost, security, privacy, and usability.

Application Areas of Biometrics

There are a number of applications where biometric systems are useful.

Few of them are given below:
 Controlling workplace access
 Identity establishment of people for authentic citizenship and immigration systems
 Applying access control to sensitive information and systems
 Identifying criminals by forensics
 Executing online e-commerce transactions
 Fraud and theft reduction
 Law enforcement
Biometrics versus traditional authentication methods:

Face Biometrics:
Facial recognition systems can be used to identify people in photos, videos, or in real-time. Facial
recognition is a category of biometric security. Other forms of biometric software include voice
recognition, fingerprint recognition, and eye retina or iris recognition.
Face Recognition Operations
The technology system may vary when it comes to facial recognition. Different software
applies different methods and means to achieve face recognition. The stepwise method is as
follows:

 Face Detection: To begin with, the camera will detect and recognize a face. The face
can be best detected when the person is looking directly at the camera as it makes it
easy for facial recognition. With the advancements in technology, this is improved
where the face can be detected with slight variation in their posture of face facing the
camera.
 Face Analysis: Then the photo of the face is captured and analyzed. Most facial
recognition relies on 2D images rather than 3D because it is more convenient to match
 to the database. Facial recognition software will analyze the distance between your eyes
or the shape of your cheekbones.
 Image to Data Conversion: Now it is converted to a mathematical formula and these
facial features become numbers. This numerical code is known as a face print. The way
every person has a unique fingerprint, in the same way, they have unique face prints.
 Match Finding: Then the code is compared against a database of other face prints. This
database has photos with identification that can be compared. The technology then
identifies a match for your exact features in the provided database. It returns with the
match and attached information such as name and address or it depends on the
information saved in the database of an individual.
Design of Face Recognition System:
At a high level, a facial recognition system relies on the following core steps:
Face Detection – Locate and isolate faces in an input image.
Feature Extraction – Analyze facial features and create a face print.
Face Matching – Compare face prints to a database of known faces to identify an
individual.
Neural Network for Face Recognition:

Facial Recognition Using Neural Network

In the past few years, face recognition has received a significant attention and regarded as

one of the most successful applications in the field of image analysis. Artificial neural

networks (ANN) have been used in the field of image processing and pattern recognition.

A general face recognition system includes many steps: face detection; feature extraction; and

face recognition. In the recent years, different architectures and models of ANN were used for

face detection and recognition.

 Face Detection in Video Sequences:
Face detection methods
Face detection software uses several different methods, each with advantages and
disadvantages:
Viola-Jones algorithm. This method is based on training a model to understand what is and
isn't a face. Although the framework is still popular for recognizing faces in real-
time applications, it has problems identifying faces that are covered or not properly oriented.
Knowledge- or rule-based. These approaches describe a face based on rules. Establishing
well-defined, knowledge-based rules can be a challenge, however.
Feature-based or feature-invariant. These methods use features such as a person's eyes or
nose to detect a face. They can be negatively affected by noise and light.
Template matching. This method is based on comparing images with previously stored
standard face patterns or features and correlating the two to detect a face. However, this
approach struggles to address variations in pose, scale and shape.
Appearance-based. This method uses statistical analysis and ML to find the relevant
characteristics of face images. The appearance-based method can struggle with changes in
lighting and orientation.
Challenges in Face Biometrics
Biometric systems can make two basic errors. A “false positive” occurs when the system
incorrectly matches an input to a non-matching template, while in a “false negative”, the
system fails to detect a match between an input and a matching template.
 Pose variation. Variation in pose causes significant problems in detecting a face. ...
 Variation in illumination. ...
 Variation in expression. ...
 Ageing. ...
 Occlusions. ...
 Similar Faces. ...
 Image Resolution.
Biometrics - Face Recognition Methods:
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 using tensor representation, and the
neuronal motivated dynamic link matching.
Advantages and Disadvantages.