Fingerprint Classifications Practical Applications of Fingerprint Classifications

Fingerprint Classifications Practical Applications of Fingerprint Classifications in Forensic Science Fingerprint identification has numerous practical applications. Particular fingerprints may be matched to individuals because they are distinct and unchanging. The individuality of fingerprints is based on the ridge structure and minutiae. The recognition of these landmarks, including shape, number, and location is an automated process by which computer algorithms filter data and match a subset of individuals with a particular print. More complex analyses are then performed to identify the individual who matches the print from the subset of prospects.

Overall, the accuracy of these technologies is extremely high and is considered the gold-standard for individual recognition. Future technologies such as DNA fingerprinting and iris scan algorithms appear promising and may replace fingerprinting in the future. Practical Applications of Fingerprint Classifications in Forensic Science Large volumes of fingerprints are collected and stored everyday for use in a wide range of applications including forensics, access control, and driver license registration.

Automatic recognition of people based on fingerprints requires that the input fingerprint be matched with a large number of fingerprints in a database. For example, the Federal Bureau of Investigation database contains approximately 70 million fingerprints (Azoury et al., 2004). To reduce the search time and computational complexity, it is desirable to classify these fingerprints in an accurate and consistent manner so that the input fingerprint is required to be matched only with a subset of the fingerprints in the database. According to most professional criminal investigators, fingerprints obey three fundamental principles.

These principles are: 1. A fingerprint is an individual characteristic. It is yet to be found that prints taken from different individuals possess identical ridge characteristics. 2. A fingerprint will remain unchanged during an individual's lifetime. 3. Fingerprints have general characteristic ridge patterns that permit them to be systematically classified. Fingerprinting analysis has been used for more than a century. However, this technology is still widely used in law enforcement agencies. Because of its unique characteristic, it is conclusive evidence and a valuable tool among advanced technology.

However, there is a chance it might lose its ground by DNA fingerprint, which is more sophisticated and accurate than traditional fingerprint. There are three types of fingerprints that may exist at crime scenes. First, visible prints are made from finger stained with colored materials such as ink, blood, and grease. In addition, plastic prints may be formed by pressing onto a soft surface such as clay, soap, and wax. Finally, a latent print is an invisible print left on an object by the body's natural greases and oils.

Because it cannot be seen by the naked eye, fingerprint powders, chemicals, and even lasers are used to make fingerprints visible on the crime scene evidence. In North America, one of the first successful uses of fingerprints for identification was by E. Henry in 1901 in order to stop the railway workers from double collecting pay (Schulz, Reichert, Wehner, & Mattern, 2004). The Henry system derives from the pattern of ridges, which are concentrically patterns on the hands, toes, feet, and fingers.

It has reliably been proven that no two individuals have identical ridge patterns, ridge patterns are not inheritable, ridge patterns are formed in the embryo, ridge patterns never change in life, and after death may only change as a result of decomposition. In life, ridge patterns are only changed by accident, injury, burns, disease or other unnatural causes. The individuality of any fingerprint may be based not upon the general shape or pattern that it forms, but instead upon its ridge structure and specific characteristics, also known as minutiae.

The recognition of these ridges, their relative number, and the approximate location of them, on the observed print, are the special characteristics that make the fingerprint a specific identifying characteristic of each individual. There are at least 150 individual ridge characteristics on the average fingerprint. If between 10 and 16 specific points of reference for any two corresponding fingerprints identically compare, a match may be assumed.

In a judicial proceeding, a point-by-point comparison must be graphically demonstrated for at least 12 different, but corresponding, points in order to prove the identity of a specific person (Maudling & Attwood, 2004). Fingerprint classification is a technique to assign a fingerprint into one of the several pre-specified types already established in the literature, which can provide an indexing mechanism. Fingerprint classification may be viewed as a coarse level matching of the fingerprints. An input fingerprint is first matched at a coarse level to one of the pre-specified types.

Then, at a finer level, it is compared to the subset of the database containing that type of fingerprints only. Algorithms have been developed to classify fingerprints into five classes. These classes include whorl, right loop, left loop, arch, and tented arch. The algorithm separates the number of ridges present in four directions (0 degree, 45 degrees, 90 degrees, and 135 degrees) by filtering the central part of a fingerprint with a bank of Gabor filters (Blotta & Moler, 2004). This information is quantified to generate a FingerCode, which is used for classification.

Classification is based on a two-stage classifier, which uses a K-nearest neighbor classifier in the first stage and a set of neural networks in the second stage. For the five-class problem, classification accuracy of 90% is typically achieved. For the four-class problem (arch and tented arch combined into one class), classification accuracy is ~95%. Identification from fingerprints requires the differentiation of uninterrupted papillary ridge contours followed by the mapping of anatomic marks or interruptions of the same ridges.

Codified in the late 1800's as Galton features, minutiae are at their most rudimentary ridge endings, the points at which a ridge stops, and bifurcations, the point at which one ridge divides into two.

Many types of minutiae exist, including dots (very small ridges), islands (ridges slightly longer than dots, occupying a middle space between two temporarily divergent ridges), ponds or lakes (empty spaces between two temporarily divergent ridges), spurs (a notch protruding from a ridge), bridges (small ridges joining two longer adjacent ridges), and crossovers (two ridges which cross each other). There are three basic fingerprint patterns: arch, loop and whorl. There are more complex classification systems that further break down the pattern to plain arches or tented arches.

Loops may be radial or ulnar. Whorls also have smaller classifications. However, the five most commonly used are: whorl, right loop, left loop, arch and tented arch. Loops make up nearly 2/3 of all fingerprints, whorls are nearly 1/3, and perhaps 5-10% are arches. These classifications are relevant in many large-scale forensic applications, but are rarely used in biometric authentication. This fingerprint is a right loop. Other features are essential to fingerprint authentication.

The core is the inner point, normally in the middle of the print, around which swirls, loops, or arches center. It is frequently characterized by a ridge ending and several acutely curved ridges. Deltas are the points, normally at the lower left and right hand of the fingerprint, around which a triangular series of ridges center. The ridges are also marked by pores, which appear at steady intervals.

Some initial attempts have been made to use the location and distribution of the pores as a means of authentication, but the resolution required to capture pores consistently is very high. Common definitions of anatomic criteria used in fingerprint analysis are described below: Ridge is defined as having double the distance from starting to ending, as neighboring ridges are wide Evading ends are two ridges with different directions run parallel with each other for more than 3mm.

Bifurcation describes where a ridge splits, both ridges maintain the same direction and are longer than 3mm Hook describes the location where a ridge splits; one ridge is not longer than 3mm Fork describes where two ridges are connected by a third ridge not longer than 3mm Dot is the ridge section is no longer than the neighboring ridges are wide Eye is the region where the ridge splits and rejoins within 3mm Island is where a ridge splits and joins again within not less than 3mm and not more than 6mm.

The enclosed area is ridgeless. Enclosed ridge is a ridge not longer than 6mm between two other ridges Enclosed loop is a non-pattern determining loop between two or more parallel ridges. The anatomic characteristics have an orientation or direction. A vector analysis of the direction change of the ridge lines can produce an average that reflects this orientation. The distance between ridge lines and anatomic feature give a length to the vector produced by orientating the anatomic characteristics.

This is dependent on the sensor reproducing repeatable results independent of pressure spread or melting of the ridgelines. Of the two types of arches, the plain arch is the simplest of all fingerprint patterns. It is formed by ridges entering from one side of the print and existing on the opposite side. These ridges tend to rise at the center of the pattern, forming a wavelike structure.

The tented arch is similar, but instead of rising smoothly at the center, there is either a sharp up thrust or spike, or the ridges meet at an angle that is less than 90 degrees. Arches do not have type lines, deltas, or cores. Type lines are two diverging ridges usually coming into and splitting around an obstruction, such as a loop. A delta is the ridge point nearest the type line divergence. The core is the approximate center of the pattern.

A loop must have one or more ridges entering from one side of the print, recurving, and exiting from the same side. If a loop opens toward the little finger, it is called an ulnar loop. If it opens toward the thumb, it is a radial loop. The patterned area of any loop is surrounded by two type lines. All loops must have one delta (Saatci & Tavsanoglu, 2003). All whorl patterns must have type lines and a minimum of two deltas.

A plain whorl and central pocket loop have at least one ridge that makes a complete circuit. This ridge may be in the form of a spiral, an oval, or any variant of a circular form. The main difference between these two patterns can be shown if an imaginary line is drawn between the two deltas contained within the two patterns.

If the line touches any one of the spiral ridges, the pattern is determined to be a plain whorl, if no ridge is touched, the pattern is a central pocket loop. The double loop is made up of any two loops combined into one fingerprint. Any print classified as accidental either contains two or more patterns or the pattern is not covered by other categories, i.e. A combination loop and a plain whorl or a loop and tented arch.

Once a high-quality image is captured, there are a several steps required to convert its distinctive features into a compact template. This process, known as feature extraction, is at the core of fingerprint technology. The image must be converted to a usable format. If the image is grayscale, the areas lighter than a particular threshold are discarded, and those areas darker are made black. The ridges are then thinned from five to eight pixels in width down to one pixel, for precise location of the endings and bifurcations.

Minutiae localization begins with this processed image. At this point, even a very precise image will have distortions and false minutiae that need to be filtered out. For example, an algorithm may search the image and eliminate one of two adjacent minutiae, as minutiae are very rarely adjacent. Anomalies caused by scars, sweat, or dirt may occasionally appear as false minutiae, and algorithms have the ability to locate any points or patterns that don't make sense, such as a spur on an island or a ridge crossing perpendicular to others.

A large percentage.