BIOMETRIC SYSTEM
What Is Biometrics?
Biometrics is a technology that is used in the security industry and is integrated with other authentication applications and technologies, like domain access, single sign-on, smart cards, encryption, remote access, and digital signatures. Biometrics authenticates you based on your unique physical body demographics or your behavioral characteristics. In other words, you can consider yourself as your password. Biometrics gives you an alternative and higher security compared to passwords or pin identification due to the fact that passwords and pin’s can easily be compromised.
Stages in Biometric System
A biometric system can be divided into two stages
- The enrollment module
- The identification module.
Logical module of a biometric system
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.
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.
Types of Biometric Systems
Biometrics comes in several different security solutions. They are divided based on whether the biometrics solution is a physical attribute or a characteristic attribute.
Physical Attributes
Ear Recognition
Face Recognition
Finger Geometry Recognition
Fingerprint Recognition
Hand Geometry Recognition
Iris Recognition
Retina Recognition
Characteristic Attributes
Gait Recognition
Odor Recognition
Signature Recognition
Typing Recognition
Voice Recognition
Face recognition
Computers of the future will interact with us more like humans. A key element of the interaction will be their ability to recognize our faces and even understand our expressions.
The most famous early example of a face recognition system is that of Teuvo Kohonen of the Helsinki University
Kohonen’s system was not a practical success, however, because it relied on precise alignment and normalization. In the following years, many researchers tried face recognition schemes based on edges, inter feature distances, and other neural-net approaches. Feret (face recognition technology) identified an algorithm that demonstrated the highest level of recognition accuracy with large databases under double blind testing conditions.
Iris recognition
The human iris promises to deliver a level of uniqueness to identification applications that other biometrics cannot match. The highly randomized appearance of the iris makes its use as a biometric well recognized. Its suitability as an exceptionally accurate biometric derives from its
- Extremely data-rich physical structure,
- Genetic independence-no two eyes are the same,
- Stability over time, and
- Physical protection by a transparent window (the cornea) that does not inhibit external view ability.
Computers of the future will interact with us more like humans. A key element of the interaction will be their ability to recognize our faces and even understand our expressions.
The most famous early example of a face recognition system is that of Teuvo Kohonen of the Helsinki University
Kohonen’s system was not a practical success, however, because it relied on precise alignment and normalization. In the following years, many researchers tried face recognition schemes based on edges, inter feature distances, and other neural-net approaches. Feret (face recognition technology) identified an algorithm that demonstrated the highest level of recognition accuracy with large databases under double blind testing conditions.
Iris recognition
The human iris promises to deliver a level of uniqueness to identification applications that other biometrics cannot match. The highly randomized appearance of the iris makes its use as a biometric well recognized. Its suitability as an exceptionally accurate biometric derives from its
- Extremely data-rich physical structure,
- Genetic independence-no two eyes are the same,
- Stability over time, and
- Physical protection by a transparent window (the cornea) that does not inhibit external view ability
Iris codes derived from this process are compared with previously generated iris codes. The difference between two iris codes is expressed as the fraction of mismatched bits, termed a hamming distance. For two identical iris codes, the HD is zero; for two perfectly unmatched iris codes, the HD is 1. For different irises, the average HD about 0.5, this indicates a 50 percent difference in the codes. For two different images form the same iris, the HD ranges from approximately 0.05 to 0.1, a variation that includes contributions from video noise as well as variations in the position of the user’s eye with respect to imaging optics. Generally, an HD threshold of 0.32 can reliably differentiate authentic users from impostors.
Multimodal biometric system
By combining face, voice, and lip movement recognition, this identification system yields highly accurate results. Because it includes a dynamic feature, it provides more security than systems using only static features.
The system records, preprocesses, and classifies each biometric feature separately. During the training (enrollment) of the system, biometric templates are generated for each feature. For classification, the system compares these templates with the newly recorded pattern. Then, using a strategy that depends on the level of security required by the application, it combines the classification results into one result by which it recognizes persons..
By combining face, voice, and lip movement recognition, this identification system yields highly accurate results. Because it includes a dynamic feature, it provides more security than systems using only static features.
The system records, preprocesses, and classifies each biometric feature separately. During the training (enrollment) of the system, biometric templates are generated for each feature. For classification, the system compares these templates with the newly recorded pattern. Then, using a strategy that depends on the level of security required by the application, it combines the classification results into one result by which it recognizes persons..
A) Data acquisition and preprocessing
The input to the system is a recorded sample of a person speaking. The one - second sample consists of a 25 - frame video sequence and an audio signal. From the video sequence, the preprocessing module extracts two optical biometric traits: face and lip movement while speaking a word. To extract those features, the preprocessing module must have exact knowledge of the face’s position. Since this recognition system should be able to function in any arbitrary environment with off - the - shelf video equipment, the face finding process is one of the most important steps in feature extraction.
B) Using hausdorff distance for face location
To detect the location of a face in an arbitrary image, model based algorithm that matches a binary model of a typical human face to a binarized, edge extracted version of the video image. After detecting the face boundaries, the preprocessing module locates the eyes from the first three images of the video sequences, under the assumption that a person often closes his eyes when beginning to speak. As with face location, eye location also relies on an image model and the hausdorff distance. Locating the eye positions allows all further processing to take place.
C) Facial features
For face recognition, the preprocessing module uses the first image in the video sequence that shows the person with eyes open. Once the eyes are in position, the preprocessing module uses anthropomorphic knowledge to extract a normalized portion of the face. That is, it scales all faces to a uniform size. This procedure ensures that the appropriate facial features are analyzed - not, for example, the head size, the hairstyle, a tie, or a piece of jewelry. After rotating and scaling the image, the preprocessing module extracts a gray scale image. Some further preprocessing steps take care of lighting conditions and color variance.
D) Lip movement
BioID collects lip movements by means of an optical - flow technique that calculates a vector field representing the local movement of each image part to the next image in the video sequence. For this process, the preprocessing module cuts the mouth area out of the first 17 images of the video sequence. It gathers the lip movement of identifiable points on the lip from frame to frame. To reduce the amount of data, we reduce the optical flow resolution to a factor of four through averaging. Finally, a 3D fast Fourier transformation of the 16 vector fields takes place. The result is a one-dimensional lip movement feature vector, which the system uses for training and classification of lip movement. Essentially, we are condensing the detailed movement defined by several vector fields to a single vector.
E) Acoustic preprocessing
We record the speech sample using a 22-kHz sampling rate with 16-bit resolution. After channel estimation and normalization, the preprocessing module divides the time signal into several smaller, overlapping windows. For each window, it calculates the cepstral coefficient, which forms the audio feature vector.
Voice recognition
We use vector quantification to classify the audio sequence. In the system - training phase, the audio preprocessing module analyzes several recordings of a single person’s voice. From each voice pattern, it creates a matrix, and the vector quantifier combines these matrices into one matrix. This matrix serves as a prototype that displays the reference voice pattern. Using this voice pattern, a minimum-distance classifier assigns the current pattern to the class showing the smaller distance.
FINGERPRINT RECOGNITION
Introduction
Fingerprint recognition has been around for quite a while and is considered as one of the most used biometrics security methods that are on the market today. Fingerprint recognition provides a great solution for door or computer room access, desktop logon authentication, and application integration just to name a few. Fingerprint recognition provides a low cost biometrics solution and with its small designs makes it a prime choice when implementing a high security solution.
What Is Fingerprint Recognition?
Fingerprint recognition is a biometric security method that integrates with applications and other technologies to provide a way to identify a person by scanning a person’s fingerprint to gain access. Fingerprint recognition is a way to provide higher security when needed due to the fact that the system does not use any passwords or pins but only valid fingerprints.
Impression made by the papillary ridges on the ends of the fingers and thumbs. Fingerprints afford an infallible means of personal identification, because the ridge arrangement on every finger of every human being is unique and does not alter with growth or age. Fingerprints serve to reveal an individual's true identity despite personal denial, assumed names, or changes in personal appearance resulting from age, disease, plastic surgery, or accident. The practice of utilizing fingerprints as a means of identification, referred to as dactyloscopy, is an indispensable aid to modern law enforcement.
Each ridge of the epidermis (outer skin) is dotted with sweat pores for its entire length and is anchored to the dermis (inner skin) by a double row of peg like protuberances, or papillae. Injuries such as superficial burns, abrasions, or cuts do not affect the ridge structure or alter the dermal papillae, and the original pattern is duplicated in any new skin that grows. An injury that destroys the dermal papillae, however, will permanently obliterate the ridges.
Any ridged area of the hand or foot may be used as identification. However, finger impressions are preferred to those from other parts of the body because they can be taken with a minimum of time and effort, and the ridges in such impressions form patterns (distinctive outlines or shapes) that can be readily sorted into groups for ease in filing.
FINGERPRINT CLASSIFICATION
Introduction
Fingerprint records are among the most significant files that are maintained. Inked fingerprints from all 10 fingers of an individual person can be classified; i.e., be put into narrow categories for file purposes and ultimate retrieval. Most countries use the Henry extension system, a modification of the Henry system, which was developed prior to 1900 in England
Fingerprints obtained from individuals are classified and compared with the fingerprints of other individuals having the same classification. With this system, personnel in a police centre need not compare a set of fingerprints with the millions of cards on file but only with the few in the same classification. (For the technique of fingerprint identification, see below Laboratory procedures.)
Classification of Fingerprints
Fingerprints are classified in a three-way process: by the shapes and contours of individual patterns, by noting the finger positions of the pattern types, and by relative size, determined by counting the ridges in loops and by tracing the ridges in whorls. The information obtained in this way is incorporated in a concise formula, which is known as the individual's fingerprint classification.
There are several variants of the Henry system, but that used by the Federal Bureau of Investigation (FBI) in the United States
patterns: radial loop, ulnar loop, double loop, central pocket loop, plain arch, tented arch, plain whorl, and accidental. Whorls are usually circular or spiral in shape. Arches have a mound like contour, while tented arches have a spike like or steeple like appearance in the centre. Loops have concentric hairpin or staple-shaped ridges and are described as “radial” or “ulnar” to denote their slopes; ulnar loops slope toward the little finger side of the hand, radial loops toward the thumb. Loops constitute about 65 percent of the total fingerprint patterns; whorls make up about 30 percent and arches and tented arches together account for the other 5 percent. The most common pattern is the ulnar loop.
Dactyloscopy, the technique of fingerprinting, involves cleaning the fingers in benzene or ether, drying them, and then rolling the balls of each over a glass surface coated with printer's ink. Each finger is then carefully rolled on prepared cards according to an exact technique designed to obtain a light gray impression with clear spaces showing between each ridge so that the ridges may be counted and traced. Simultaneous impressions are also taken of all fingers and thumbs.
Latent fingerprinting involves locating, preserving, and identifying impressions left by a culprit in the course of committing a crime. In latent fingerprints, the ridge structure is reproduced not in ink on a record card but on an object in sweat, oily secretions, or other substances naturally present on the culprit's fingers.
Most latent prints are colorless and must therefore be “developed,” or made visible, before they can be preserved and compared. This is done by brushing them with various gray or black powders containing chalk or lampblack combined with other agents. The latent impressions are preserved as evidence either by photography or by lifting powdered prints on the adhesive surfaces of tape. Fingerprint files and search techniques have been computerized to enable much quicker comparison and identification of particular prints.
Other “fingerprinting” techniques have also been developed. These include the use of a sound spectrograph—a device that depicts graphically such vocal variables as frequency, duration, and intensity—to produce voice graphs, or voiceprints, and the use of a technique known as DNA fingerprinting, an analysis of those regions of DNA that vary among individuals, to identify physical evidence (blood, semen, hair, etc.) as belonging to a suspect. The latter test has been used in paternity testing as well as in forensics.
Fingerprint Patterns
Finger patterns (from top left to bottom right): loop, double loop, central pocket loop, plain whorl, plain arch, and tented arch
WORKING OF FINGERPRINT RECOGNITION
How Does Fingerprint Recognition Work?
Because there are several fingerprint recognition solutions that are available today, we will just consider a general overview of how fingerprint recognition can work.
• The first step is to setup your fingerprint recognition device and scan all fingerprints that will be granted access. You will only need to do this once as the fingerprint recognition device stores the fingerprints as templates in a mathematical algorithm form. Depending on your setup, the device may store this in a database or use smart card technology for local storage of these fingerprint templates.
• When an individual wants access, the individual must put their finger on the fingerprint recognition device or depending on the type of system, you may only need to put it close to the fingerprint scanning area. The fingerprint recognition device then captures the individual’s fingerprint and puts in into a template form using a mathematical algorithm and compares it to its database or storage of fingerprints to determine if it matches any existing fingerprints. If the fingerprint device finds a match then access is granted.
As we noted above, this example may vary from vendor to vendor. If you’re looking for more in-depth fingerprint recognition security information, then you should contact a biometric security vendor to request more information.
FINGERPRINTS IN CRIME
Crime Investigation Using Fingerprints?
Fingerprints found at the scene of a crime can be evidence connecting an individual with a crime. Fingerprints can be either visible or latent. Visible prints—formed by dirt or blood, for example—or three-dimensional prints formed in soft matrices can be photographed directly. Latent fingerprints, which are not ordinarily visible, can be brought out by dusting techniques when the surface is hard and by chemical techniques when the surface is porous.
In dusting for fingerprints, a fine powder of contrasting color is applied with a fine brush. The powder clings to the residual oils and fats in the print and the excess powder is removed with the brush. On porous surfaces such as paper, fuming iodine, silver nitrate, or ninhydrin solutions are used to develop the latent fingerprints. The most effective developer of latent fingerprints is ninhydrin, which can reveal prints that are several years old.
Fingerprints are identified on the basis of agreements in a significant number of individualities, commonly known as “points.” These are the bifurcations, ending ridges, and dots in the fingerprint pattern. If sufficient points are found with spatial relationship to other points, a basis exists for identifying a fingerprint. It was formerly considered necessary to have 12 points to identify a fingerprint, but in current practice, a lesser number is often used. Palm prints and footprints are identified in the same manner as fingerprints.
The record-keeping tasks of police work were long handled by using a diversity of manual systems. Quick nationwide or international utilization of records and files was impossible. Now, however, electronic data processing has revolutionized information-handling techniques. Manual filing systems have been superseded by computers that operate from central geographic points, storing data and making it instantaneously and accurately available to many police constituents.
Advances in computer networking permit the linking of many police and investigative data bases and make possible the development of national criminal investigation systems. Interpol is an example of an international computer network that coordinates the exchange of criminal intelligence to aid police agencies in searching for fugitives or missing persons or property.
In addition to serving as a depository and dispenser of information, the computer can provide statistical analysis for research and management, develop intelligence data bases and analysis systems, assist in the analysis of physical evidence, facilitate swift document retrieval, and help in such areas as identification of fingerprints.
Using traditional manual methods, fingerprint examiners, for example, have to make visual comparisons of thousands of individual 10-digit fingerprint cards in order to make a positive identification. The development of a computerized fingerprint search system took more than 20 years of industry-wide research. Although the Federal Bureau of Investigation was a pioneer in the development of automated fingerprint files, the vast size of its collection of fingerprint cards and the high cost of converting its files delayed the completion of a high-speed fingerprint search system. The Japanese National Police Agency established the first practical system in Tokyo
A second generation of the Japanese system focused on individual images instead of 10-digit cards. Since its introduction, this system has been used as a prototype for several computerized systems in the United States
ISSUES AFFECTING PERFORMANCE OF THE BIOMETRIC SYSTEMS
The major issues affecting the performance of the biometric systems can be listed as
Follows:
1. Accuracy
If a legitimate biometric characteristic is presented to a biometric-based authentication system, correct authentication cannot be guaranteed. This could be because of sensor noise, limitations of the processing methods, and, more importantly, the variability in both the biometric characteristic as well as its presentation. And there is also the possibility that an impostor could be incorrectly authenticated.
2. Cost
Cost is tied to accuracy. Many applications-like logging in to a PC -are sensitive to the additional cost of including biometric technology. Given the increasing availability of inexpensive processing power -mass - scale production of inexpensive sensors - it will become possible to make biometrics accessible to new personal identification applications; increased usage of the sensors may lower their prices even more.
3. Integrity
Authentication is of no use if the system cannot provide assurance that the legitimate owner indeed presented the characteristic. Data from multiple, independent biometric characteristics can serve to reinforce the identity of a subject. Multiple biometrics can alleviate several other practical problems in biometrics-based personal identification. Consequently, the integration of multiple biometric systems will become increasingly important. In “BioID: A Multimodal biometric identification system,” Robert w. frischholz and Ulrich dieckmann describe a mutibiometric system that is based on integrating face ad voice biometrics.
4. Ease of use
It is likely that obtrusive cumbersome biometric authentication systems will be avoided much like we avoid systems requiring long passwords.
5. Privacy
Despite its obvious strengths, there are a few negative preconceptions about biometrics that often result in the following question: will biometric data be used to track people, secretly violating their right to privacy? Thanks to sensational reporting and hype, there is a disparity between perception and reality when it comes to abuses of biometric technology.
6. Ease of development
To foster improvements and encourage widespread deployment, biometric technology needs to be made easily accessible for system integration and implementation. Harnessing and integrating biometric technology is not easy in its present form; one of the reasons is the lack of industry-wide standards.
APPLICATIONS OF BIOMETRICS
The government’s interest in biometric technologies is motivated by the desire to improve the delivery of services to citizens by increasing efficiency and convenience while decreasing costs and fraud. However, the very personal nature of this technology raises concerns about its potential impact on personal freedoms.
1. Drivers licensing.
2. Immigration.
3. Employment eligibility.
4. Welfare.
5. Airport security.
