Biometrics refers to metrics related to human physiognomies. Biometrics authentication is widely used in computer science as a form of identification and access control. Biometric science & techniques makes effective use of measuring and analyzing biological data. Biometric verification is any means by which a person’s identity can be distinctively confirmed by evaluating one or more of his distinguishing biological traits. Unique identifiers used in Biometric Technology include hand geometry, fingerprints, eye iris and retinal patterns, earlobe geometry, facial patterns, hand geometry and measurements, human voice, DNA, vein recognition and signatures. The oldest & most accepted form of biometric verification is fingerprint identification. In today’s epoch, Biometric verification has achieved considerable advancements with the dawn of computerized databases with digitization of analog data, allowing almost instantaneous personal identification using biometrics.
Fingerprint recognition is the most effective and largely utilized method of biometrics used to identify and verify the identity of an individual. This is because fingerprints are one of those inexplicable twists of nature that all human beings happen to naturally have built-in, literally at their fingertips. All humans have tiny ridges and valleys of skin on their fingertips, formed through a combination of genetic and environmental factors, building unique fingerprints for each human being. Even identical twins have unique fingerprints. Such unique biometric trait set the platform to build fingerprint recognition systems.
Fingerprint recognition or fingerprint authentication is an automated method of verifying a match between fingerprints, by comparing a live fingerprint with previously stored database of fingerprints.
Fingerprint sensor is the most important module in a biometric fingerprint recognition system. A fingerprint sensor is an electronic module or device used to capture a digital image of the fingerprint outline. The captured image is termed as live scan. This live scan is digitally processed to create and store a biometric template and which is later used for fingerprint matching or identification purposes. Listed below is a synopsis of few of the more universally used fingerprint sensor technologies.
Capacitance or Capacitive Fingerprint Sensors
Capacitance sensors use principles of capacitance to form fingerprint images. In this method of imaging, the sensor array’s pixels, each, act as one plate of a parallel-plate capacitor, the electrically conductive dermal layer acts as the other plate, and the non-conductive epidermal layer acts as a dielectric.
Optical Fingerprint Sensors
Optical fingerprint sensor technique is most commonly used fingerprint sensor technology. Optical fingerprint imaging captures a digital image of the finger print using visible light. This type of sensor is, in essence, a specialized digital camera. The top layer of the sensor, where the finger is placed, is known as the touch surface. Beneath this layer is a light-emitting phosphor layer which illuminates the surface of the finger. The light reflected from the finger passes through the phosphor layer to an array of solid state pixels, a charge-coupled device, which captures a visual image of the fingerprint. Most advanced versions of optical sensors use sophisticated methods to identify live fingerprints. This technology is termed as optic sensor over semiconductor film, OSSF fingerprint sensors that use advanced semiconductor films that are capable of analyzing live finger prints utilizing electro-static science technique that a live & healthy human being leaves as a signature.
Ultrasonic Fingerprint Sensors
Ultrasonic sensors utilize of the doctrines of medical ultrasonography in order to create visual images of the fingerprint. Unlike optical imaging, ultrasonic sensors use very high frequency sound waves to penetrate the epidermal layer of skin. The sound waves generated using piezoelectric transducers & reflected energy is then measured using piezoelectric materials. Since the dermal skin layer exhibits the same characteristic pattern of the fingerprint, the reflected wave measurements can be used to form an image of the fingerprint. This technology is expensive to implement, however, eliminates the need for clean, undamaged epidermal skin at the fingerprints.
Passive Capacitance Fingerprint Sensors
A passive capacitance sensor use similar principle of capacitance to form an image of the fingerprint patterns on the dermal layer of skin. Each sensor pixel is used to measure the capacitance at that point of the array. The capacitance varies between the ridges and valleys of the fingerprint due to the fact that the volume between the dermal layer and sensing element in valleys always contain an air gap. The dielectric constant of the epidermis and the area of the sensing element are known values. The measured capacitance values are then used to distinguish between fingerprint ridges and valleys forming the fingerprints.
Active Capacitance Fingerprint Sensors
Active capacitance sensors use a charging cycle to apply a voltage to the skin before measurement takes place. The application of voltage charges the effective capacitor. The electric field between the finger and sensor follows the pattern of the ridges in the dermal skin layer. On the discharge cycle, the voltage across the dermal layer and sensing element is compared against a reference voltage in order to calculate the capacitance. The distance values are then calculated mathematically, and in turn used to form an image of the fingerprint. Active capacitance sensors measure the ridge patterns of the dermal layer in a technique similar to the ultrasonic system. Again, this is an expensive technique to implement, however, eliminates the need for clean, undamaged epidermal skin at the fingerprints.
Fingerprint Sensor Algorithms
Matching algorithms are used to compare previously stored templates of fingerprints with live fingerprints for user authentication purposes. In order to do this either the original image must be directly compared with the user’s fingerprint image or certain features of the finger print must be compared.
Pattern-based (or image-based) Finger Recognition Algorithms
Pattern based algorithms compare the basic fingerprint patterns (arch, whorl, and loop) between a previously stored template and a candidate fingerprint. This requires that the images can be aligned in the same orientation. To do this, the algorithm finds a central point in the fingerprint image and centers on that. In a pattern-based algorithm, the template contains the type, size, and orientation of patterns within the aligned fingerprint image. The candidate fingerprint image is graphically compared with the template to determine the degree to which they match.
Benefits of fingerprint identification technology in automation systems include:
Effective usage of fingerprint identification technology: Fingerprint identification is widely accepted in, Law Enforcement Forensics, Civil Identification, Background Checking, Employment, Adoption/Foster Parenting, Border Control/Visa Issuance, work force management, Physical Access Control, Logical/Network Access Control, Identity Verification for International Travel Documents (passports, visas), Device Access Control (e.g., PDAs, mobile devices), Identity Theft Protection, Payments Authorization etc.
A facial recognition system is typically a computer application for identifying or verifying a person from a digital image source or a video frame from a video source. Face Recognition is achieved by comparing selected facial features from the live face image to a facial database. Face recognition technology is typically used in security systems for user identification or detection. Facial recognition biometrics is similar to other biometrics techniques such as fingerprint recognition biometrics or eye iris recognition systems. Listed below are few of the commonly used facial recognition techniques.
Biometric Systems incorporating Face Recognition Technology are a touch-free, hygienic alternative to fingerprint systems and hand readers. Human face comprises of several distinct landmarks, the different peaks and valleys which together form facial features that are used as nodal points in a face recognition system. Every human face consists of approximately 80 of these nodal points. Few of such nodal points considered to represent a human face in the database are:
Traditional Face Recognition Techniques
Several facial recognition algorithms identify facial features by extracting face features from an image of the user's face. For example, an algorithm may analyze the relative position, size, and/or shape of the nose, eyes, cheekbones, and jawline etc. These features are then used to search previously stored images to match facial features. Other algorithms normalize a gallery of face images and then compress the face data, only saving the data in the image that aids in face recognition. A live user’s face image is then compared with the stored face data. One of the earliest successful systems were based on template matching techniques applied to a set of salient facial features, providing a sort of compressed face depiction.
Face Recognition Algorithms are divided into two main approaches, geometric, which looks at distinguishing features, or photometric, which is a statistical approach that distills an image into values & compares these values with templates to eliminate changes. Most prevalent recognition algorithms include Principal Component Analysis using Eigen faces, Elastic Bunch Graph Matching using the Fisher face algorithm, Linear Discriminate Analysis, the Multilinear Subspace Learning using tensor representation, the Hidden Markov model and the neuronal motivated dynamic link matching.
3-dimensional (3D) Face Recognition Technology
A newly emerging face recognition trend is three-dimensional face recognition. This technique uses 3D sensors to capture data about the shape of a face. This information is then used to identify distinctive features on the surface of a face, such as the contour of the eye sockets, nose shape & length, and chin dimensions etc. to achieve the most accurate face recognition. Earlier technology relied on 2D image to identify face. However, for a 2D face recognition technology to work accurately, the image captured needed to be of a face that was looking almost directly at the camera. A slight variance of light or facial expression from the image in the database, could reduce the effectiveness of a 2D face recognition system.
In order to overcome the underperformance of 2D face recognition systems, 3D face detection technology with improved accuracy in face detection was developed. To effectively capture a real-time 3D image of a user’s facial surface, 3D face recognition uses distinctive features of the face such as the curves of the eye socket, nose and chin where rigid tissue and bone is most apparent, is used. These facial areas are always unique and do not change with time. These features are not affected by lighting conditions. 3D recognition technique also effectively recognizes users at different view angles of up to 90 degrees.
A key advantage of 3D facial recognition is that it is not affected by changes in lighting like other techniques. 3D face recognition technique can also identify a face from a range of viewing angles, including a profile view. 3D research is boosted by the development of sophisticated 3D sensors which do better capturing 3D face images. The sensors work by projecting controlled light onto the face of the user. More than a dozen of these 3D image sensors can be placed on the same CMOS chip—each sensor captures a different part of the spectrum, enhancing the captured imagery.
Matching of a user’s image is easier if database contains 3D images, and the captured image of the user trying to identify is also in 3D format. 3D technique provides a live, moving variable subject being compared to a flat, stable image. New technology is addressing this challenge. When a 3D image is taken, different points (usually three) are identified. For example, the outside of the eye, the inside of the eye and the tip of the nose will be pulled out and measured. Once those measurements are in place, an algorithm (a step-by-step procedure) will be applied to the image to convert it to a 2D image. After conversion, the software will then compare the image with the 2D images in the database to find a potential match.
In verification mode, a face image is matched with only one image in the database (1:1). If user identification is required, then the image is to be compared to all images in the database resulting in a score for each potential match (1:N).
To summarize, 3D facial recognition is the most reliable technique and represents the future of face recognition technology.
Skin Texture Analysis
Another emerging trend uses the visual details of the skin, as captured in standard digital or scanned imagery. This technique is called skin texture analysis, works by converting the unique lines, patterns, and spots apparent in a person’s skin into a mathematical space. With the addition of skin texture analysis in a face recognition system, its performance in recognizing faces can increase 20 to 25 percent.
Finger vein recognition is a technique of biometric verification that uses pattern-recognition techniques based on images of human finger vein patterns beneath the skin's surface. Finger vein recognition is one of many forms of biometrics used to identify individuals and verify their identities. Finger Vein ID is a biometric authentication system that matches the vascular pattern in an individual's finger to previously stored database. Finger vein ID systems are currently put to use or under development for a wide variety of applications, including employee time and attendance tracking, computer and network authentication, credit card authentication, automobile security, end point security, automated teller machines etc.
To store a vein the pattern for the database storage, user inserts a finger into an attester terminal containing a near-infrared LED (light- emitting diode) light and a monochrome CCD (charge-coupled device) camera. The hemoglobin in the blood absorbs near-infrared LED light, which makes the vein system appear as a dark pattern of lines. The camera records the image and the raw data is digitized, certified and stored into a database of registered images. Blood vessel patterns are unique to each individual. Unlike some biometric systems, blood vessel patterns are almost impossible to forge since they are located beneath the skin's surface. The finger vein ID system is much harder to cheat because it can only authenticate the finger of a living person.
Vein matching, also called vascular technology, is a technique of biometric identification through the analysis of the patterns of blood vessels visible from the surface of the skin. Though used by the FBI & CIA, this method of identification is still under development and has not yet been universally adopted by crime labs as it is not considered as trustworthy as more established techniques, such as fingerprinting. However, it can be used in combination with existing forensic data to derive proper conclusions whenever required.
While other types of biometric scanners are more popular for security systems, Vascular scanners are growing in popularity. Since fingerprint scanners require direct contact of the finger with the scanner, dry or scratched skin can interfere with the consistency of the system. Skin diseases, such as psoriasis can also limit the accuracy of the scanner, not to mention direct contact with the scanner can result in need for more frequent cleaning and higher risk of equipment damage. Vascular scanners do not require contact with the scanner, and since the information they read is on the inside of the body, skin conditions do not affect the accuracy of the reading. Vascular scanners also work with extreme speed, scanning in less than a second. As they scan, they capture the unique pattern veins take as they branch through the hand. Compared to the Retinal Scanner, which is more accurate than the vascular scanner, the retinal scanner has much lower popularity, because of its invasive nature. People generally are uncomfortable exposing their eyes to an unknown light. Also, retinal scanners are more difficult to install, since variances in height and face angle must be accounted for.
Iris recognition is an automated method of biometric identification that uses mathematical pattern-recognition techniques on video images of one or both of the irises of an individual's eyes, whose complex random patterns are unique, stable, and can be seen from some distance.
Iris recognition uses video camera technology with subtle near infrared illumination to acquire images of the detail-rich, intricate structures of the iris which are visible externally. An iris recognition algorithm can identify up to 200 identification points including rings, furrows and freckles within the iris of a user. First the system has to confine the inner and outer boundaries of the iris (pupil and limbus) in an image of an eye. Further subroutines detect and exclude eyelids, eyelashes, and specular reflections that often block parts of the iris. The set of pixels containing only the iris, normalized by a rubber-sheet model to compensate for pupil dilation or constriction, is then analyzed to extract a bit pattern encoding the information needed to compare two iris images.
The iris has a fine texture that—like fingerprints—is determined randomly during embryonic conception. Like the fingerprint, it is very hard & impossible to prove that the iris is unique. However, there are so many factors that go into the formation of these textures (the iris as well as fingerprint) that the chance of false matches for either is exceedingly low. Even genetically identical individuals, and even the left and right eyes of the same individual, have completely independent iris textures.
Iris recognition works perfectly even with clear contact lenses, eyeglasses, and non-mirrored sunglasses. However, there are several shortcomings of iris recognition systems. These include many commercial iris scanners can be easily fooled by a high quality image of an iris or face in place of the real thing. Iris recognition is very difficult to perform at a distance larger than a few meters. It also is more difficult if the person to be identified is not cooperating by holding the head still and looking into the camera. Iris recognition is susceptible to poor image quality, with associated failure to enroll rates. Iris scans also cannot achieve live-tissue verification.
Eye vein verification is a technique of biometric authentication that applies pattern-recognition techniques to video images of the veins in a candidate’s eyes. The complex and random patterns are unique, and modern hardware and software can detect and differentiate those patterns at some distance from the eyes.
The veins in the sclera — the white part of the eyes — can be recorded when a person glances to either side, providing four regions of patterns: one on each side of each eye. Verification employs digital templates from these patterns, and the templates are then encoded with mathematical and numerical algorithms. These allow confirmation of the identity of the user. One of the technology’s strengths is the stability of the pattern of eye blood vessels. These patterns do not change with age, allergies, alcohol abuse or redness. Eye veins are clear enough that they can be reliably imaged by the cameras on most smartphones. The technology works through contacts and glasses, however, not through sunglasses. At least one version of eye vein detection uses infrared illumination as part of the imaging, allowing imaging even under low lighting conditions.
Eye vein verification, like other methods of biometric authentication, can be used in a range of security situations, including mobile banking, government security, and in healthcare environments.
Voice or Speaker recognition is the identification of a user from characteristics of voices, also known as voice biometrics. Voice recognition biometrics utilizes the acoustic features of speech that have been found to differ between individuals. These acoustic patterns reflect both composition (e.g., size and shape of the throat and mouth) and learned behavioral patterns (e.g., voice pitch, speaking style). Voice recognition biometrics is as such classified as a "behavioral biometric identification technique".
The various tools used to process and store voice prints include frequency estimation, hidden Markov models, Gaussian mixture models, pattern matching algorithms, neural networks, and matrix representation, Vector Quantization and decision trees. Some systems also use "anti-speaker" techniques, such as cohort models, and world models.
Ambient noise levels can impede both collections of the initial and subsequent voice samples. Noise reduction algorithms can be employed to improve accuracy, but incorrect application can have the opposite effect. Performance degradation can result from changes in behavioral attributes of the voice and from enrolment using one telephone and verification on another telephone ("cross channel"). Integration with two-factor authentication products is expected to increase. Voice changes due to ageing may impact system performance over time. Some systems adapt the speaker models after each successful verification to capture such long-term changes in the voice, though there is debate regarding the overall security impact imposed by automated adaptation.
Voice recognition technology traditionally uses existing microphones and voice transmission technology allowing recognition over long distances via ordinary telephones. Digitally recorded audio voice identification and analogue recorded voice identification uses electronic measurements as well as critical listening skills that must be applied by a forensic expert in order for the identification to be accurate.