Fingerprint Classification and Forensic Identification Methods

Introduction to Fingerprint Identification

Large volumes of fingerprints are collected and stored every day for use in a wide range of applications including forensics, access control, and driver's license registration. Automatic recognition of people based on fingerprints requires that the input fingerprint be matched against 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 search time and computational complexity, it is desirable to classify these fingerprints in an accurate and consistent manner so that the input fingerprint need only be matched against a subset of the fingerprints in the database.

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 that 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 eventually replace traditional fingerprinting.

Principles and History of Fingerprint Analysis

According to most professional criminal investigators, fingerprints obey three fundamental principles:

1. A fingerprint is an individual characteristic. No prints taken from different individuals have yet been found to 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.

Fingerprint analysis has been used for more than a century and remains widely used in law enforcement agencies. Because of its unique characteristics, it constitutes conclusive evidence and is a valuable tool even among advanced technologies. However, it may eventually be superseded by DNA fingerprinting, which is more sophisticated and accurate than traditional fingerprinting.

There are three types of fingerprints that may exist at crime scenes. First, visible prints are made from fingers stained with colored materials such as ink, blood, and grease. Second, plastic prints may be formed by pressing onto a soft surface such as clay, soap, or wax. Finally, a latent print is an invisible print left on an object by the body's natural greases and oils. Because latent prints cannot be seen by the naked eye, fingerprint powders, chemicals, and even lasers are used to make them visible on 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 railway workers from double collecting pay (Schulz, Reichert, Wehner, & Mattern, 2004). The Henry system derives from the pattern of ridges, which are concentrically arranged on the hands, toes, feet, and fingers. It has reliably been proven that no two individuals have identical ridge patterns, that ridge patterns are not inheritable, that ridge patterns are formed in the embryo, and that ridge patterns never change in life. After death, ridge patterns may only change as a result of decomposition. During life, they are altered only by accident, injury, burns, disease, or other unnatural causes.

The individuality of any fingerprint is based not upon the general shape or pattern it forms, but rather upon its ridge structure and specific characteristics, also known as minutiae. The recognition of these ridges, their relative number, and their approximate location on the observed print are the special characteristics that make a fingerprint a specific identifying feature of each individual. There are at least 150 individual ridge characteristics on the average fingerprint. If between 10 and 16 specific points of reference on any two corresponding fingerprints match identically, 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).