Fingerprint Analysis

A fingerprint is the reproduction of a fingerprint epidermis, produced when a finger is pressed against a smooth surface. The most evident structural characteristic of a fingerprint is a pattern of interleaved ridges and valleys; in a fingerprint image as shown in Figure

Figure 1 finferprint structure

Ridges (also called ridge lines) are dark whereas valleys are bright. Injuries such as superficial burns, abrasions, or cuts do not affect the underlying ridge structure and the original pattern is duplicated in any new skin that grows. Ridges and valleys run in parallel; sometimes they bifurcate and sometimes they terminate. When analyzed at the global level, the fingerprint pattern exhibits one or more regions where the ridge lines assume distinctive shapes (characterized by high curvature, frequent termination, etc.,). These regions (called singularities or singular regions) may be classified into three typologies: loop, delta, and whorl. Singular regions belonging to loop, delta, and whorl types are typically characterized by ∩, ∆, and O shapes, respectively. Sometimes whorl singularities are not explicitly introduced because a whorl type can be described in two facing loop singularities. For fingerprints that not contain loop or whorl singularities, it is difficult to define the core. In these cases, the core is usually associated with the point of maximum ridgeline curvature. Unfortunately, due to the high variability of fingerprint patterns, it is difficult to reliably locate a registration (core) point in all the fingerprint images. Singular regions are commonly used for fingerprint classification that is, assigning a fingerprint to a class among a set of distinct classes, with the aim of simplifying search and retrieval. At the local level, other important features, called minutiae can be found in the fingerprint patterns. Minutia means small detail; in the context of fingerprints, it refers to various ways that the ridges can be discontinuous. For example, a ridge can suddenly come to an end (termination), or can divide into two ridges (bifurcation). Although several types of minutiae can be considered (the most common types are shown in Figure 2(a), usually only a coarse classification is adopted to deal with the practical difficulty in automatically discerning the different types with high accuracy. The FBI minutiae coordinates model considers only terminations and bifurcations [8]. Each minutia is denoted by its class, horizontal (xo) and vertical (yo) coordinates and the angle between the tangent to the ridgeline at the minutia position and the horizontal axis as shown in Figure 2 (b) and (c).

In practice, an ambiguity exists between termination and bifurcation minutiae; depending on the finger pressure against the surface where the fingerprint is left, terminations may appear as bifurcations and vice versa (this property is known as termination/bifurcation duality). In fact, each ridge of the epidermis (outer skin) is dotted with sweat pores along its entire length and anchored to the dermis (inner skin) by a double row of peglike protuberances, or papillae. Although more information (number, position, shape, etc.,) is highly distinctive, very few automatic matching techniques use pores since their reliable detection requires very high resolution and good quality fingerprint images. It is necessary to employ image enhancement techniques prior to minutiae extraction to obtain a more reliable estimate of minutiae locations. The response of a matcher in a fingerprint recognition system is typically a matching score (without loss of generality, ranging in the interval (0, 1)) that quantifies the similarity between the input and the database template representations. A typical biometric verification system commits two types of errors: mistaking biometric measurements from two different fingers to be from the same finger (called false match) and mistaking two biometric measurements from the same finger to be from two different fingers (called false non-match) [9]. Note that these two types of errors are also often denoted as False Acceptance Rate (FAR) and False Rejection Rate (FRR) respectively. The biometric testing literature discusses accuracy in terms of the likelihood of these types of errors. The FRR and FAR for a biometric system always depend on the match threshold and are always inversely related [3]. For a given system, it is not possible to reduce both error rates simultaneously. Depending on the purpose of the system, one type of error might be preferred over the other. The best setting is a result of balancing user convenience (few false rejects) with security objectives (few false accepts), and carefully considering the costs and risks of each error type in context.  are becoming a vital part of the transformation to a more technologically integrated society. Current fingerprint technologies are generally susceptible to acquiring poor quality images due to different skin conditions and environmental effects. These poor quality images adversely affect the ability to accurately determine a person’s identity. But most of the fingerprint sensors can be a treat and enhance this poor image and then use it.