Automated Fingerprint Identification System

From Wikipedia, the free encyclopedia

Automated Fingerprint Identification System (or AFIS) is a system to automatically match one or many unknown fingerprints against a database of known prints. This is done for various reasons, not the least of which is because the person has committed a crime. With greater frequency in recent years, AFIS like systems have been used in civil identification projects. The intended purpose is to prevent multiple enrollment in an election, welfare, DMV or similar system.

IAFIS, the 'I' meaning 'integrated', holds all fingerprint sets (called tenprints) collected in the US, and is managed by the FBI.

1 International use
2 Technology
3 Types of fingerprinting
4 Methods
5 See also
6 External links

[edit] International use

Many other nations, including Canada, the United Kingdom, Israel, Australia and the International Criminal Police Organization, as well as many states and local administrative regions, have their own AFIS, which are used for a variety of purposes, including criminal identification, applicant background checks, receipt of benefits, and receipt of credentials (such as passports).

[edit] Technology

The machine used to scan fingerprints into AFIS is called the LiveScan Device. The process of obtaining the prints by way of laser scanning is called LiveScan. The process of obtaining prints by putting a tenprint card (prints taken using ink) is occasionally called DeadScan or CardScan. In addition to these devices, there are other devices to capture prints from crime scenes (latent prints), as well as devices (both wired and wireless) to capture one or two live fingers. The most common method of acquiring fingerprint images remains the inexpensive ink pad and paper form. Scanning forms ("fingerprint cards") in forensic AFIS complies with standards established by the FBI and NIST.

To match a print, a fingerprint technician scans in the print in question, and the computer marks all minutiae points according to an algorithm. In some systems, the technician then goes over the points the computer has marked, and submits the minutiae to a one-to-many (1:n) search. Increasingly, there is no human editing of features necessary in the better commercial systems. The fingerprint image processor generally will assign a "quality measure" that indicates if the print is useful for searching.

[edit] Types of fingerprinting

Fingerprint matching algorithms vary greatly in terms of Type I (false positive) and Type II (false negative) errors. They also vary in terms of features such as image rotation invariance and independence from a reference point (usually, the "core", or center of the fingerprint pattern). The accuracy of the algorithm, robustness to poor image quality and the characteristics noted above are critical elements of system performance.

[edit] Methods

Fingerprint matching has an enormous computational burden. Some larger AFIS vendors deploy custom hardware while others use highly optimized software to attain matching speed and throughput. In general, it is desirable to have, at the least, a two stage search. The first stage will generally improve access precision by use of global fingerprint characteristics such as "pattern type combinations" while the second stage is the minutiae matcher.

In any case, the search systems return results with some numerical measure of the probability of a match (a "score"). In tenprint searching using a "search threshold" parameter to increase accuracy, there should seldom be more than a single candidate unless there are multiple records from the same candidate in the database. Many systems use a broader search in order to reduce the number of missed identifications, however, and these searches can return from one to ten possible matches. Latent to tenprint searching will frequently return many - often fifty or more - candidates because of limited and poor quality input data. The validation of computer suggested candidates is usually done by a technician in forensic systems. In recent years, though, "Sure-Hit" algorithms produce "Identified" responses without a human operator looking at the prints, provided the matching score is high enough. "Sure-Hit" is often used in civil identification systems, and is increasingly used in criminal identification systems as well.