AFIS: Fingerprint Identification And AI Essay, Research Paper
Fingerprint identification existed in its simplest forms long before it was used for solving crimes. Pre-historic picture writing of a hand with ridge patterns was discovered in Nova Scotia. In ancient Babylon, fingerprints were used on clay tablets for business transactions. In ancient China, thumbprints were found on clay seals. In 14th century Persia, various official government papers had fingerprints (impressions), and one government official, a doctor, observed that no two fingerprints were exactly alike. This could be considered the first observation that led to the science of fingerprint identification. In 1686, Marcello Malpighi, a professor of anatomy at the University of Bologna, noted in his treaties; ridges, spirals and loops in fingerprints, however he made no mention of their value as a tool for individual identification. A layer of skin was named after him; “Malpighi” layer, which is approximately 1.8mm thick and has the raised ridge pattern that we now use. During the 1870’s, Dr. Henry Faulds, the British Surgeon-Superintendent of Tsukiji Hospital in Tokyo, Japan, took up the study of “skin-furrows” after noticing finger marks on specimens of “prehistoric” pottery. A learned and industrious man, Dr. Faulds not only
recognized the importance of fingerprints as a means of identification, but devised a method of classification as well. In 1880, Faulds forwarded an explanation of his classification system and a sample of the forms he had designed for recording inked impressions, to Sir Charles Darwin. Darwin, in advanced age and ill health, informed Dr. Faulds that he could be of no assistance to him, but promised to pass the materials on to his cousin, Francis Galton. Also in 1880, Dr. Faulds published an article in the Scientific Journal, “Nautre” (nature). He discussed fingerprints as a means of personal identification, and the use of printers ink as a method for obtaining such fingerprints. He is also credited with the first fingerprint identification of a greasy fingerprint left on an alcohol bottle.
Sir Francis Galton, a British anthropologist , began his observations of fingerprints as a means of
identification in the 1880’s. In 1892, he published his book, “Fingerprints”, establishing the individuality and permanence of fingerprints. The book included the first classification system for fingerprints.
Galton’s primary interest in fingerprints was as an aid in determining heredity and racial background. While he soon discovered that fingerprints offered no firm clues to an individual’s intelligence or genetic history, he was able to scientifically prove what Faulds already suspected: that fingerprints do not change over the course of an individual’s lifetime, and that no two fingerprints are exactly the same. According to his calculations, the odds of two individual fingerprints being the same were 1 in 64 billion.
Galton identified the characteristics by which fingerprints can be identified. These same characteristics (minutia) are basically still in use today, and are often referred to as Galton’s Details.
The year 1901 marked the first introduction of fingerprints for criminal identification in England and Wales, using Galton’s observations and revised by Sir Edward Richard Henry. Thus began the Henry Classification System, used even today in all English speaking countries. In 1924, an act of congress established the Identification Division of the FBI. The National Bureau and Leavenworth consolidated to
form the nucleus of the FBI. fingerprint files. By 1946, the FBI had processed 100 million fingerprint cards.
Now the database consists of over 250 million fingerprint cards.
Why Fingerprint Identification? Fingerprints offer an infallible means of personal identification. That is the essential explanation for their having supplanted other methods of establishing the identities of criminals reluctant to admit previous arrests. Other personal characteristics change – fingerprints do not. Around 1870 a French anthropologist devised a system to measure and record the dimensions of certain bony parts of the body. These measurements were reduced to a formula which, theoretically, would apply only to one person and would not change during his/her adult life. This Bertillon System, named after its inventor, Alphonse Bertillon, was generally accepted for thirty years. But it never recovered from the events of 1903, when a man named Will West was sentenced to the U.S. Penitentiary at Leavenworth, Kansas. There was already a prisoner at the penitentiary at the time, whose Bertillon measurements were nearly exact, and his name was William West. Upon an investigation, there were indeed two men. They looked exactly alike, but were allegedly not related. Their names were Will and William West respectively. Their Bertillon measurements were close enough to identify them as the same person. However, a fingerprint comparison quickly and correctly identified them as two different people. The West men were apparently identical twin brothers per indications in later discovered prison records citing correspondence from the same immediate family relatives.
Why do people leave fingerprints? The sweat glands in the skin of the fingertips produce a water based oil solution that coats the ridges of the print. These ridges retain a portion of this solution such that when the finger makes contact with a surface, a residue is left behind which is a facsimile of the print (i.e., latent print). It is this characteristic which gives the biometric devices the ability to electronically scan and analyze a given print.
Common Types of Fingerprints:
1. ROD. A Rod generally forms a straight line. It has little to no curved features and tends to be found in the center of the fingerprint’s pattern area.
2. ELLIPSE. An Ellipse is a circular or oval shaped line-type, which is generally found in the center of Whorl patterns.
3. SPIRAL. A Spiral line-type spirals out from the center of the fingerprint and is generally found in whorl print patterns.
4. BIFURCATION. Is the intersection of two or more line-types, which converge or diverg
5. TENTED ARCH. Resembles a tent. This line-type quickly rises and falls at a steep angle. They tend to be associated with Tented Arch pattern prints.
6. ISLAND. An Island is a line-type, which stands alone. (i.e., does not touch another line-type and is totally contained in the pattern area of interest).
7. SWEAT GLAND. The finger contains many sweat glands. The moisture and oils they produce actually allow the fingerprint to be electronically imaged.
8. ARCH. Arch line-types can be found in most print patterns. Fingerprints made up primarily of arches are sometimes classified as Arch prints.
9. MINUTIAE POINTS. Is the term used to define common micro features in a fingerprint. Common minutiae points are the intersection of bifurcation, ending points of Islands and the center point of the sweat glands
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 individuals fingerprint classification. There are several variants of the Henry system, but that used by the Federal Bureau of Investigation (FBI) in the United States
recognizes eight different types of 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 center. 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.
Automated Fingerprint Identification System (AFIS) – is an algorithmic software for fingerprint search matching and fingerprint recognition. It uses the FBI/Yale/Los Alamos [W]avelet-packet [S]calar [Q]uantization fingerprint compression algorithm (WSQ). Which is the standard compression algorithm for scanned fingerprint images. It preserves an acceptable quality of the print, while taking up only a fraction of the space that a normally encoded JPG file would. This, of course, helps with the speed of the search and keeps the fingerprint database manageable.
Fingerprint scan quality can affect the reliability of any electronic fingerprint system. In general, automated fingerprint analysis systems work by creating a computer model of the live print scan.
This model is based on many of the features found to be common in fingerprints and is sometimes referred to as a template. The process of creating this model/template is usually referred to as a ‘Registration’ process. Due to a lack of natural moisture in the skin, a dry print can appear broken or incomplete to the electronic imaging system. This can result in inferior model construction during a registration process or inconsistent matching during a look-up process. The process of matching a live print scan to a model/template is generally referred to as a ‘Lookup’. Dry skin can be caused by a multitude of climatic and environmental conditions. Handling materials or substances tend to absorb or wash the oils from the print. Items such as paper, cloth, wood or chemicals (i.e., acetone, thinners, cleaning agents etc.) will have a direct result on the dryness of the fingers. These items tend to absorb or wash oils from the skin leaving the ridges void of the necessary moisture to reliably electronically image the print. Excessive moisture in the skin can cause line-type features in the print to blend together during the registration or look-up process resulting in inferior constructs or inconsistent look-ups. An excessively wet print is analogous to viewing a painting after a puddle of paint has been poured on it. Excessive moisture is generally caused by sweating or handling wet materials or substances. Common sources are greasy foods , hand lotion or makeup. The condition is easily solved by removing the excess moisture. Scar tissue has plastic like qualities. When it is dry, it does not image well, when it is wet it looks like a puddle to the imaging system.
The AFIS system uses a unique form of ‘Vector Analysis’. It starts by taking a raster scan at an effective resolution of 1000 dots per inch (DPI). Then it makes several passes on the raster data to clean up and optimize the image. This is followed by a raster to vector conversion process. In short, it intelligently converts raster pixels into vector line types, which are then used to classify the print. Vector analysis generalizes the print through standard classification methods and is therefore very tolerant of micro feature changes or print contamination. This built in tolerance allows the system to be used in applications where other identification systems would be unreliable. The system is trained to analyze and classify a print in the same manner that a fingerprint expert would (only better, easier and faster). The system identifies all Common Line-types (shapes) as described above as well as other pertinent distinguishing marks or relative characteristics of the scanned print/image. In addition, the pattern area can be classified according to industry accepted rules.
All of the analysis is performed by the system and an encrypted print model is generated for optional transmission to a central site for verification. This model (once de-encrypted) represents an access key to the central database for one to one (1:1) or one to many (1:N) lookups. The system consistently maps a scanned print into a fixed coordinate system such that the print always has the same general origin. With this feature, the systems can be used to generate index keys for large existing fingerprint databases. These indexes in turn allow for very fast real time personnel identification.