Biometrics is best defined as measurable physiological and / or structural behavioural characteristics that can be utilized to verify the identity of an individual. They include finger prints, retinal and iris scanning, hand geometry, voice patterns, facial recognition and other techniques. They are of interest in any area where it is important to verify the true identity of an induvidual. Initally, these techniques were employes primarily in specialist high security applications, however we are now seeing their use and proposed used in a much broader range of public facing situations.
Why do we have to go in for biometrics identification systems?
all along we have been using PINs and ID cards as a means of identification, but these are limited in their scope. for they offer a means for identificaton of the PIN or the ID card and not the person who has produced it. we may easily recognize the ID card but it could be presented by anybody else. this is totally overcome through processes used in biometrics as is discussed in this web site.
An ID card can be transferred from one person to another but a biometric can not be transferred from one person to another (we are discouting replacement part surgery).
What is it all about?
Based on the biometrics tecnology, we have systems that use physical characteristics unique to an individual-the pattern in the iris, hand geometry, voice prints and even body odour- for identifing a person. So how significant is this going to be in the future? Well, this technology is set to replace computer passwords for granting or denying access to computer resourses. just imagine how it would be to log on to windows using a swipe of your finger the blink of an eye and use your voice to access your yahoo mail account.
What happens here is that biological features identified through computerized iris scanning or palm scanning are matched aganist a digital file containing information on thoes exact characteristics. Even keystroke typing rhythms can be mapped and digitized for identification. The advantages of such system are many. Biometrics identification, by default is far more secure than any other identification methods currently in use, especially since the person needs to be physically present at the point of identification. An added advantage is that there is no need to carry an identification tag or remember a password.
The Intricacies
Esentialy a biometric system follow two characteristic traits: identification and verification. The former involves identifying a person from all biometric measurments collected in a database. The question is that this process seeks to answer is "Do I know who you are?". It, therefore, involves a one-compared-to-many match, also reffered to as a 'cold search'. Verification involves authenticating a person's claimed identity from his/her perviously enrolled pattern. "Are you who you claim to be?" is the question that this process seeks to answer. This involves a one-to-one match.
The biometric system generally works through five phases:
Data Collection
Transmission
Signal Processing
Data Storage
Verification
In the beginning, a sensor reads some physiological or behavioural characteristic unique to an individual. The biometric system processes and stores the data on the measuring device or transfers as a part of central database. Sometimes the data would require compression for quick transfer. The compression algorithm should be properly selected to ensure that there is no loss of data during compression.
Biometric data is by nature variable. Hence, a straight comparision of the collected sample with another sample from the database is usually inadequate. Instead, a pattern-matching process has been devoloped using feature extraction algorithm techniques and adaptive systems such as neural networks. Under this pattern-matching process, a presented feature sample is compared to a stored sample called a template. The comparision result in the form of a quantitative measure is sent to the decision subsystem.
Decision-making is based on statistical methods, whereby the average of several samples is calculated and a normal distrbution of the biometric data with a mean value and standard deviation is formulated. The quantiative distance between the sample and template must lie within certain threshld to be accepted as a match, or it is rejected. However, unless the system is perfectly fine-tuned this decision-making is prone to false rejaction and acceptance. This aspect of the selection process is discussed in detail in later parts of the web site.
Popular Biometric Methodologies
We have seen that bioimetric identification system are probably the best-suited means of identification of people. But, how exactly is this done is the question. The following is a list of the most popular methodologies used to identify a person:
Fingerprint Verification
Hand Geometry
Voice Verification
Retinal Scanning
Iris Scanning
Signature Verification
Ficial Verification
Now we shall see a bit of all these methods and the hand geometry based verification method alone in detail.
Fingerprint Verification:
There are varity of aproches to finger print verification. some of them try to emulate the traditional police method of matching minutiae, others are staright pattren matching devices, and some adopt a unique approach all of their own, including moire fringe patterns and ultrasonics. Some of them can detect when a live finger is presented, some cannot. There is a greater variety of fingerprint devices avaliable than any other biometric at present.
Potentially capable of good accuracy (low instances of false acceptance) fingerprint devices can also suffer from usage error amoung insufficiently disiplined users (higher instances of false rejection) such as might be the case with large user bases. One must also consider the transducer/ user interface and how this would be effected by large scale usage in a variety of environments. Finger print varification may be a good choice for in house systems where adequate explanation and training can be provided to users and where the system is operated within a controlled environment. It is not surprising that the work station access application area seems to be based almost exclusively around fingerprints, due to the relatively low cost, small size (easily integrated into keyboards) and ease of integration.
Hand Geometry:
As the name suggests, hand geometry is concerned with the physical characteristics of the user's hand and fingers, from a three dimensional prespective. One of the most established methodologies, hand geometry offers a good balance of performance, characteristics and is relatively easy to use. This methodology may be suitable where we have large user bases or user who may access the system infrequently and may therfore be less disiplined in there approach to the system. Accuracy can be very high if desired, whilst felexible performance tuning and configuration can accomodate a wide range of applications. Hand geometry readers are deployed in a wide range of scenarios. includind time and attendance recording where they have proves exterimly popular. Ease of integration into other systems and processes, coupled to ease of use makes hand geometry an obvious first step for many biometric projects.
Voice Verification:
A potentially interesting bearing in mind how much voice communication takes place with regard to everyday business transactions. Some designs have concentrated on wall-mounted readers whilst other have sought to integrate voice verification into conventional telephone handsets. Whilst there have been a number of voice verification products introduced to the market, many of them have suffered in practice due to variability of both transducers and local acoustics. In addition, the enrollment procedure has often been more complicated than with other biometrics leading to the perception of voice verification as unfriendly in some quarters. However, much work has been and continues to be undertaken in this context and it will be interesting to monitor progress accordingly.
Retinal Scanning:
An established technology where the unique patterns of the retina are scanned by a low intensity light source via an optical coupler. Retinal scanning has proved to be quite accurate in use but does require the user to look into the receptacle and foucus on the given point. This is not particularly convienent if you are a spectacle wearer or have concern about intimate contact with a reading device. For these reasons retinal scanning has a few user acceptance problems although the technology itself can work well. The leading product underwent a redesign in the mid nineties, providing enhanced connectivity and an improved user interface, however this is still a relatively marginal biometric technology.
Iris Scanning:
Iris scanning is undoublty the less intrusive of the eye related biometrics. It utilizes a fairly conventional CCD camera element and requires no intimate contact between user and reader. In addition it has the potential for higher than average template matching performance. As a technology it has attracted the attention of various third party integrators and one would expect to see additional products launched in due coarse as a result. It has been demonstrated to work with spectacles in place and with a variety of ethinic groups and is one of the few devices, which can work weel in identification mode. Ease of use and system integration have not traditionally been strong points with the iris scanning devices, but we can expect to see improvements in these areas as new products are introduced.
Signature Verification:
Signature verification enjoys a synergy with existing processes that other biometrics donot. People are used to signatures as a mean of transaction related identity verification and would mostly see nothing unusual in extending this to encompass biometrics. Signature verification devices have proved to be reasonably accurate in operations and obviously lend themselves to applications where the signature is an accepted identifier. Curiously, there have been relatively few significant applications to date in comparision with other biometric methodologies. If your application fits, it is a technology worth concidering , although signature verification vendors have tended to have a somewhat chequered history.
Facial Recognition:
A technique which has attracted conciderable interest and whoes capabilities have often been misunderstood. Extravagant claims have sometimes been made for facial recognition devices that have been difficult if not impossible to substantiate in practice. It is one thing to match two static images (all that some systems donot infact biometrics at all), it is quite another to un obtrusively detect and verify the identity of an individual within a group (as some system claims). It is easy to understand the attraction of facial regonition from the user perspective, but one needs to be realistic in ones expectation of the technology. To date, facial recognition system have had limited success in practical applications. However, progress continues to be made in this area and it will be interesting to see how future implementations performs. If technical obstacles can be overcome, we may eventually see facial regonition become a primary biometric methodolgy.
There are other biometric methodologies including the use of scent, ear lobes, and various other parameters. Whilst these may be technically interesting, they are not concidered at this stage to be workable solutions in everyday applications.
