Biometrics are the physical characteristics of human beings used for automated recognition. A biometrics system is an automated identification system, which uses the physiological and behavioral characteristics of human beings for individualization. It is a modern and digitized system for human identification and verification.
Physiological characteristics are the traits that are physically present in the human body. For example, fingerprints, iris, facial features, DNA, etc. while behavioral characteristics are the traits acquired by an individual through the day-to-day social environment. For example- the voice, handwriting, gait pattern, etc.
A biometric system is a pattern recognition device that acquires physical or behavioral data from an individual, extracts a salient feature set from the data, compares this feature set against the elements set stored in the database, and provides the result of the comparison.
Characteristics of Biometric Systems
The selection of biometric systems is dependent on the type of characteristic considered for the identification and verification. But all types of biometric systems have the following characteristics in common:
- Universality– Every individual who is using the biometric application must possess the trait.
- Uniqueness– The trait must show a sufficient difference across individuals comprising the population.
- Permanence– The given biometric trait should not change significantly over a period of time.
- Measurability– The trait should be easy to get and digitize and should not cause inconvenience to the individual. It should also be amenable to process further in order to extract features from the acquired data.
- Performance– The recognition accuracy and the resources acquired to achieve that accuracy must meet the constraints imposed by the individual.
- Acceptability– Individuals that will access the biometric device should be willing to present their biometric traits to the system.
- Circumvention– It refers to the ease with which the trait of a person can be imitated or copied by using artifacts (e.g. fake fingers in case of physical and mimicry in case of behavioral traits). The biometric system should be immune to circumvention.
Historically biometrics was introduced in the 1800s when Alphonse Bertillone used body measurements for identification purposes. Then in the 1880s, Edward Henry developed the identification method for fingerprints.
The development of biometrics got an acceleration in the 1900s when apart from fingerprints other biological characteristics such as facial recognition, iris, DNA, etc. also gained popularity for identification purposes. At present all the biometric systems are automated and digitized.
Every biometric system used in identification and verification is composed of four modules, namely:
- Sensor Module– This module uses scanning and reading for acquiring the raw biometric data. The quality of raw data is influenced by the scanning or camera device that is used.
- Quality Assessment and Feature Extraction Module– This module is used for assessing acquired raw data. The raw data is subjected to a signal enhancement algorithm to improve its quality. This data is then processed and a set of salient features are extracted to represent the underlying trait which is stored in the database and is referred to as a template.
- Matching and Decision-Making Module– In this module, the extracted templates are matched against the stored templates and a matching score is given. On the basis of the matching score, the identity of a person is validated or ranked.
- System Database Module– This module acts as storage for a biometric system. During the enrolment process, the template extracted from raw biometric data is stored in the database along with some biographic information such as the name, address, etc. of the user.
Types of Biometric Systems
The biometric system is broadly categorized into two divisions, based on the characteristics used for the purpose of identification. They are:-
There are various physiological/biological characteristics of every human being which make them unique among others. These traits are present in them since their birth and can not be manipulated throughout their life.
Following biometric systems use these physiological/biological traits as the core features for the purpose of identification, verification, and individualization of a human individual:
- Fingerprint Biometrics- Fingerprints are one of the first impressions which are used for the purpose of identification and verification. Fingerprints are the patterns of ridges and valleys present on the tips of the fingers of every human individual. The Integrated Automated Fingerprint Identification System (IAFIS) is a national automated fingerprint identification and criminal history system maintained by the Federal Bureau of Investigation (FBI). In India, the fingerprint identification system will be used as the NAFIS(National Automated Fingerprint Identification System). It has been launched in India on 17th August 2022.
- Iris Biometrics- Iris is the colored part of the eye. It is the annular region of the eye bounded by the pupil and sclera. The pattern of the iris is a permanent feature of the human eye which remains as it is throughout life. The IRIS (Iris recognition immigration system) program was started by the UK government that enabled more than a million registered travelers to enter the country via several British airports using only automatic iris recognition for identification, instead of passport presentation or any other means of asserting identity. The steps involved in this recognition system are:
a. Iris image acquisition
b. Localization and normalization
c. Image enhancement
d. Feature extraction
e. Enrollment in database
- Face Biometrics- Facial recognition is the automated system that captures and identifies the facial features of an individual human being on the basis of an image or video which is then matched to the facial image stored in a facial biometric database. Basically, the geometry of the face is studied by the software such as the distance between the eyes, the distance from the chin to the forehead, etc. In 2012 the FBI launched the Interstate Photo System Facial Recognition Pilot project in three states, and as of June 2014, the system was fully deployed.
- Ear Biometrics- Ear biometrics uses the shape of the external ear as the identification feature. It measures the ear’s acoustic using special headphones and inaudible sound waves. A microphone inside each earphone measures sound waves as they reflect from the ear canal, bouncing in different directions of the ear canal’s distinct curves. A digital copy of the ear shape transforms into a biometric template for later use.
- DNA Biometrics- DNA is the genetic material of human beings which is one of the most unique features of every individual. It is usually found at the crime scene in the form of biological evidence. DNA can be extracted from the biological evidence and can be directed to the identification techniques which identify the variable number of tandem repeats (VNTRs) in the DNA strands and then match them with the stored databases. One of the famous databases for DNA biometrics is the FBI’s CODIS(Combined DNA Identification System), which identifies and stores DNA information in databases.
- Palm Biometrics- Palm biometrics uses the geometry of the palm for identification purposes. Similar to the fingers, the palms of every individual have patterned ridges and grooves which form the palm impression. The palm area is wider than the area of the fingers therefore the palm is expected to have more patterned features. In May 2013, the FBI launched a Palmprint database that assists crime investigators in positive identification of criminals.
The external environment has an important effect on human behavior. There are certain characteristics that human being adapts from their’ day-to-day social environment that defines the character of an individual.
These are the behavioral characteristics that make an individual different from others. Now it is possible to trace these behavioral traits and use them in biometric analysis. The following mentioned biometric systems use the various unique behavioral traits to identify and individualize an individual human being:
- Signature Biometrics- Signature biometrics identifies an individual on the basis of the handwriting pattern of a person. The signature contains unique biometric data, such as the writing rhythm, acceleration, and pressure. This system measures how a signature is created.
- Keystroke Biometrics- It is an evolving biometric system that uses the pattern of keystrokes produced by an individual human. It is believed that every person has a unique pattern of how they press the keys of a keyboard.
- Gait Pattern Biometrics– Gait pattern is the pattern of walking of an individual human. Gait is a behavioral biometric and is influenced by a number of factors such as body weight, walking surface, footwear, nature of clothing, etc. It is one of the new biometric techniques introduced as identification procedures.
- Voice Biometrics- Voice biometrics, also known as speech recognition, is an automated system that uses the voice or speech of an individual for identification purposes. Voice is produced by the combination of movements of the vocal tract, nasal cavity, and mouth. The features of a voice include the tone, pitch, pace, accent, etc. which makes one’s speech unique. It is a biometric system that involves both the physical and behavioral characteristics of an individual.
Significance of Biometrics
Biometrics usually serves two services- Identification and Verification.
For the purpose of identification, the biometric system identifies the features and matches them with the templates stored in the database. This system conducts one too many comparisons. While in verification mode, the biometric system compares the biometric features of a person who claimed identity, with the templates stored in the database. Unlike the identification mode, it uses a one-to-one comparison.
Since it is an automated system, it has a few limitations such as-
- FMR (False Match Rate) – Mistaking biometric measurement from two different persons to be from the same person.
- FNMR (False Non-Match Rate)– Mistaking two biometrics measurements from the same person to be from two different persons.
Biometrics is an automated identification and verification system. Accurate and reliable identification is an important issue in crime investigation. With the advancement of technology, biometrics is a boon in the field of crime detection.
The biometric system uses different types of unique physiological and behavioral features of an individual for the purpose of identification and verification. Various biometrics have been developed such as facial recognition, iris biometrics, ear biometrics, fingerprint biometrics, voice biometrics, etc. while a few biometrics such as gait biometrics, keystroke biometrics, odor biometrics, etc. are emerging biometrics.
Also Have a Look at:
- What are the conventional methods to develop latent fingerprints?
- What is Henry’s 10 digit classification of fingerprints?
- Can Lip prints Help in identification of an Individual
Frequently Asked Questions
1. What Are The Security Risks Associated With Biometrics?
The common potential risks associated with Biometrics are Data Breach, Identity Theft, and Privacy violations. Since it is unique to each individual and cannot be changed, they are vulnerable since they can be misused by the parties having their access. They are also vulnerable to spoofing attacks where a hacker can access sensitive data using a fake biometric sample.
2. Are Biometric Systems More Secure Than Traditional Methods?
With the constant advancements in society, new technologies are coming making it more useful and effective than before. Similarly, biometrics are of the modern era and traditional methods like passwords and PINs are going out of trend. Biometrics are also more secure and faster. This makes them an ideal method for security.
3. Costing of Implementing a Biometric System For Security?
Biometrics is surely an effective way to security and is essential and beneficial for a business. However, before implementing the same, cost should be considered. The cost of implementing a biometric system in a business includes the cost of hardware, software, installation and maintenance fees, training, and support.