In fact, fingerprints were founded as far back as 2000 BC, as a means of a legal signature in the very primitive business transactions which took place during that time. The first true research paper which attempted to examine the unique structures of the fingerprint was published around 1694, and the very first fingerprint classification system evolved in 1823, by a scientist known as Jan Purkinje. And of course, at the turn of the century, beginning in the early 1900’s, law enforcement agencies here in the United States started to use fingerprints as the primary means to track down known suspects and criminals.
The following statistics just further exemplify the popularity of using fingerprints as the primary means of the verification and/or identification of individuals:
- You submit an article and the appropriate copy to an online lead generation business;
- Your article/copy gets downloaded, and the people who have downloaded that particular article become sales prospects;
- These sales prospects (or sales leads) are then transmitted to you by the lead generation company.
Obviously, in order to keep up with the growing demand for the use of fingerprints, the FBI devised the Automated Fingerprint Identification System, or AFIS, in order to automate fingerprint based searches across levels of law enforcement, at the national, state, and local levels. And in order to keep up with the growing demands of this gargantuan database, the Integrated Automated Fingerprint Identification System, or IAFIS, was introduced, with enhanced features. The details of this can seen in Chapter 1. An image of a fingerprint can be seen in Figure #3.
But, in the world of biometrics, the details of the fingerprint are broken down into three distinct levels:
- Level 1: The pattern images which are present in the fingerprint;
- Level 2: The minutae points of the fingerprint (this is from where a bulk of the unique features are actually extracted from);
- Level 3: This includes the shapes and the images of the ridges, and its associated pores.
The Unique Features
It is important to note at this point that mist of the biometric based fingerprint systems only collect images at Levels 1 and 2 only, it is only the most powerful fingerprint recognition systems which collect Level 3 details, and is used primarily for identification purposes. The Level 1 specific features include the following:
- Arches: These are the ridges which just flow in one direction, without doubling back, or going backwards. These only comprise about 5% of the features of the fingerprint;
- Loops: In this feature, the ridges go backwards, and go from either the left to the right or the right to the left. There are two distinct types of loops: a) Radial loops which go downward; and b) the ulnar loop which goes upwards on the fingerprint. These make up 65% of the features within the fingerprint;
- Whorls: The ridges in the fingerprint make a circle around a core, and these comprise 30% of the features in the fingerprint.
In addition to the above features which are collected by a fingerprint recognition system, the actual number of ridges, and the way that these ridges are positioned (specifically their orientation) can also prove to be a very distinctive feature as well, and can help to contribute to the verification and/or identification of an individual. Other distinctive features which can be extracted, but are not as commonly used, include the following:
- Prints/islands: These are the very short ridges found on the fingerprint;
- Lakes: These are the special indentations/depressions located right in the middle of the ridge;
- Spurs: These are the actual crossovers from one ridge to another.
The Process of Fingerprint Recognition
Fingerprint recognition is one those Biometric technologies which works not only well for verification types of scenarios, but it also works very effectively for identity applications as well, which is best exemplified by the gargantuan databases administered by the FBI. But whether it is identification or verification which is being called for, fingerprint recognition follows a distinct methodology which can be broken down into the following steps:
- Raw Data Acquisition: The actual, raw images of the fingerprint are acquired through the sensor technology which is being utilized (a detailed review of various sensors can be seen in Chapter 1). At this point, a quality check is also included. This means that the raw images which are collected are eventually examined by the biometric system to see if there is too much extraneous data in the fingerprint image, which could interfere in the acquisition of unique data. If there is too much of an obstruction found, the fingerprint device will automatically discard that particular image, and prompt the end user to place their finger into the platen for another raw image of the fingerprint to be collected. If the raw images are accepted, they are subsequently sent over to the processing unit, which is located within the fingerprint recognition device;
- With the raw images which have now been accepted by the system, the unique features are then extracted, and then stored as the enrollment template. If fingerprint recognition is being used by a smartphone, a smart card is then utilized to store the actual enrollment template, and can even provide for some processing features for the smartphone;
- Once the end user wishes to gain physical or logical access, he or she then has to place their finger onto the sensor of the fingerprint recognition system, so that the raw images and unique features can be extracted as described up above, and this becomes the enrollment templates. The enrollment and verification templates are then compared to one another, to determine the degree of similarity/non-similarity with one another;
- If the enrollment and verification templates are deemed to be close in similarity, the end user is then verified and/or indentified, and is then granted wither physical or logical access to which they are seeking.
Methods Of Fingerprint Collection
Fingerprint images can be collected in one of two methods (or even both, if the need be). They are as follows:
- Offline scanning;
- The use of Live Scan Sensors.
Offline scanning methods have been in existence since fingerprints have been used in law enforcement. These traditional methods have involved using an inked impression of an individual’s finger, and then placing that impression onto a piece of paper. Subsequently, cards were utilized instead of paper in order to store the inked fingerprint image. These were kept in file cabinets, and when a suspect was apprehended, their fingerprints were then compared to the inked fingerprint image stored on the card.
Over time, as technology improved, these two dimensional images were then scanned into a digital format, translated into a 500 DPI, in order to meet the FBI requirements and specifications. But, with today’s fingerprint recognition systems, a law enforcement officer in the field with a wireless biometric device can scan a suspect’s fingerprint, and then have that image automatically uploaded into a central server, from where it can then be converted into a proper fingerprint digital image.
As one can imagine, the use of these traditional methods definitely has its fair share of flaws. For instance, it takes great skill to get a good inked impression of a fingerprint, too little ink used means that the print area of the particular finger can be missed, and too much ink used could very well obscure any features which were attempted to gather. But, the offline methods does possess one great advantage over the live scan method. And that is, a “rolled” impression of the fingerprint can be gathered, which means that a much larger image of the fingerprint can be captured, versus the much smaller scan areas of the live scan sensors.
To this degree, the question often gets asked, is how are the latent fingerprints captured? Latent fingerprints are those which get left behind at a crime scene, and are collected later in the course of an investigation. Offline scanning methods are used to collect these latent fingerprint images at a later point in time, and often times, chemical reagents and processes are used to collect the fingerprints.
With live scan sensors, two methods of collecting fingerprints images are used:
With the touch method, direct contact is required of the finger onto the biometric sensor. But, using this type of method possesses some grave disadvantages. For instance, the platen can become dirty or smudged quite easily, any fingerprints left behind on the sensor or platen by another user previously can lead to substantial errors, and in terms of dollars and cents, there is a positive correlation between the size of the scan area and the actual cost of the sensor. Also, some sensors may not be able to capture raw images if the finger is off more than by 20 degrees from the platen.
Unlike the touch method where only finger is scanned, the sweep method captures images of multiple fingerprints as they are read by the fingerprint sensor, and from that point, multiple images are captured at the end of the sweep. From these multiple images, one composite image is created. The quality of the raw images which are captured are also partially dependent (as well as the other variables just described) on the accuracy of the reconstruction algorithm whose primary function is to compile the multiple, raw images into one image of the fingerprint.
The biggest disadvantage of the sweep method is that a much higher rate of error is introduced due to the variance in the sweeping rates and the angles. It is the sweep method which is primarily used by fingerprint recognition devices today, and there are three types of sensors which are available:
- Optical sensors: These are the most commonly used;
- Solid state sensors: The image of the raw fingerprint is captured onto a silicon surface, and the resultant image is then translated into electrical signals;
- Ultrasound sensors: This is where acoustic signals are sent towards the finger, and then a receiver subsequently digitizes the echoes from the acoustic signals.
The Matching Algorithm
As mentioned, it is the matching algorithm which compares the enrollment template with the verification template, and in order to ascertain the degree of similarity or closeness between the two, a certain methodology must be followed, and this is described as follows:
- Whatever data is collected from the raw image of the fingerprint, it must have some sort of commonality with the enrollment biometric template which is already stored in the database. This intersection of data is known as the core, which is also the maximum curvature in a ridgeline.
- Any extraneous objects which could possibly interfere with the unique feature extraction process must be removed, before the process of verification/identification can actually occur. For example, some of these extraneous objects can be the various differences found in the size, pressure, and the rotation angle of the fingerprint, and these can be normalized and removed by the matching algorithm.
- In the final stage, the unique features collected from the raw data (which actually becomes the verification template) must be compared to that of the enrollment template later. At this, point, this is where the matching algorithm does a bulk of its work. The actual matching algorithm can be based upon the premise of three types and kinds of correlations:
- Correlation Based Matching: When two fingerprints are overlaid amongst each other, or superimposed, differences at the pixel level are calculated. Although it is strived for, perfect alignment of the superimposed fingerprint images is nearly impossible to achieve. Also, a disadvantage with this correlation method is that performing these types of calculations can be very processing intensive, which can be a grave strain on computing resources.
- Minutae based matching: In fingerprint recognition, this is the most widely used type of matching algorithm. With this method, it is the distances and the angles between the minutae which are calculated and subsequently compared with another. There is global minutae matching as well as local minutae matching, and the latter method focuses upon the examination of a central minutae, as well as the nearest two neighboring minutae.
- Ridge Feature Matching: With this matching method, the minutae of the fingerprint are combined with other finger based features such as shape and size, the number and the position of various singularities, as well global and local textures. This technique comes to of great value if the raw image of the fingerprint is poor in quality, and these extra features can help compensate for that deficit.
Fingerprint Recognition-The Advantages & Disadvantages
Although fingerprint recognition is one of the dominant biometric technologies available today, it is very important to take an objective view of it, from the standpoint of its advantages and disadvantages. Remember, biometric technology is just that-just another piece of a security tool. It has its fair share of flaws just like anything else. Therefore, it is critical to examine these variables as well.
By looking at the advantages and disadvantages of any Biometric system, as a C-Level Executive, you will be in a much better position in order to make the best procurement decision possible. The advantages and disadvantages of fingerprint recognition, as well as the other biometric technologies reviewed in this chapter, will be examined from seven different perspectives, and they are as follows:
- Universality: Every human being has fingerprints. And, although a majority of the world’s population can technically be enrolled into a fingerprint recognition system, a small fraction cannot, and thus, a manual system must be put into place in order to confirm the identity of these particular individuals;
- Uniqueness: The uniqueness of the fingerprint is essentially written by the DNA code which we inherit from our parents. As a result, even identical twins are deemed to have different fingerprint structures. Interestingly enough, although the uniqueness of the fingerprint is accepted worldwide, there have been no concrete scientific studies to prove this hypothesis. So, the uniqueness of the fingerprint is still in theory only, unless it is supported by hardcore scientific tests and the results prove it;
- Permanence: Although the basic features of a fingerprint do not change as we get older over time, the fingerprint is still very much prone to degradation from conditions which exist in the external environment, such as cuts, contact with corrosive chemicals, etc.;
- Collectablity: This refers to the collection of the actual raw image of a fingerprint. But unlike other biometric technologies (especially the non-contactless ones), fingerprint recognition can be affected by a number of key variables which can degrade the quality of the raw image(s) collected. These variables include moist, oily, and dirty fingers; excessive direct pressure (this is pressing the finger too hard on the sensor) as well as rotational pressure (this means that the finger rolls side to side on the sensor); dirt and oil left on the sensor; as well as residual fingerprint left by previous users (also known as latent fingerprints). Another disadvantage is that fingerprint recognition requires very close contact on part of the end user, thus rendering this technology almost useless for high level surveillance and identification (one to many) applications;
- Performance: This is composed of two variables: Accuracy, and the ability to meet the specific requirements of the customer. The accuracy of a fingerprint recognition system is based upon such factors as the number of fingers which are used for both verification and identification applications; the quality and robustness of the matching algorithms utilized; and the size of the database which holds the fingerprint biometric templates. Under this performance umbrella, fingerprint recognition offers a number of key advantages:
- Due to the sheer number of vendors (the number of biometric vendors are amongst the largest in the biometric industry) in the marketplace translates to much lower pricing when compared to the products and solutions of other biometric vendors;
- Since fingerprint recognition is probably the most widely used biometric technology, this translates into easy training programs for the end user(s);
- The size of the biometric template (both enrollment and verification templates) is very small, on the range of 250 bytes to 1 kilobyte;
- Due to the advancements in fingerprint recognition technology, very small sensors have been created, thus allowing for this technology to be used on small portable devices like netbooks and smartphones.
- Acceptability: This evaluation criteria involves to what degree fingerprint recognition can be accepted by society as a whole. While a majority of the world’s population are accepting of fingerprint recognition, there are also serious objections to using it, and are described as follows:
- Privacy Rights Issues: This is where the use of fingerprint biometric templates fall outside of their intended uses, which further results in the degradation of the sense of anonymity;
- Concerns over hygiene: All fingerprint biometric systems require direct, human contact with the sensor. For example, the sensor can become contaminated with germs from other users of the system, which can be easily transmitted;
- There is a strong association with fingerprints and criminal activity. This is so because fingerprints have been the hallmark of law enforcement for the past number of centuries.
- Resistance to circumvention: This refers to the point as to how well a fingerprint biometric system is hack proof. Meaning, to what degree can a biometric system be resistant to security threats and risks posed to it from outside third parties. While fingerprint recognition is mostly hacker proof, it does possess a number of vulnerabilities. Probably the biggest flaw is that of latent fingerprints which can be left behind in a sensor. As a result, these latent prints can be used to produce what is known as “dummy prints”, and these could be used to possibly fool a biometric system. But also, keep in mind, that while this scenario is a possibility, all fingerprint biometric systems require that a live fingerprint be read-one that is supported with a temperature, electrical conductivity, and blood flow. This greatly reduced the risk of spoofing.
Market Applications of Fingerprint Recognition
As mentioned throughout numerous times in these chapters, fingerprint biometrics is the most widely used biometric technology, therefore, it serves a wide number of market applications, and some of the following are just examples of its enormous breadth and depth:
- Forensics: The most common example is that of capturing latent fingerprints;
- The administration of government benefits: The goal here is to 100% verify the identity of people who, are entitled to receive government benefits and entitlements, and to make sure that they are properly received;
- Use in financial transactions: Fingerprint recognition is the most widely used for accessing cash at ATM machines worldwide; and allowing for cashless transactions. This works by associating the identity of a verified individual to that of a checking or savings account (or any other source of funds) from which money can be withdrawn, after the fingerprint is presented to the biometric system. A perfect example of this are the use of fingerprint recognition systems at grocery stores. For example, some grocery stores allow for customers to pay for their products with a mere scan of their finger. The amount is then subsequently deducted from the customer’s checking account which is tied to their biometric template;
- Physical and Logical Access: This is probably the biggest market application for fingerprint recognition systems. Physical access refers to gaining access into buildings, or other secured areas from within inside a physical infrastructure. Logical access refers to gaining access to computer networks, corporate intranets, and computers and laptops themselves. In this regard, fingerprint recognition is the most widely used technology for Single Sign On Solutions (also known as a SSO’s). Meaning, instead of having to enter in a password, all one has to is present their fingerprint to the device, and in less than one second that individual can be logged into their computer.