Biometrics

Topic: Biometrics

Introduction

The purpose of this paper is to undertake a review of biometric identification. Firstly, an overview of biometric are discussed from a historical perspective, focusing on the rapid change of biometrics into the new technology. Following that, this paper will consider a brief definition of biometric identification and the substantive science which is refer to statistical and mathematical methods and biological sciences. Next, Forensic Application such as terrorist identification will be discuss in relation to FaceIT recognition. The evidence, collection and preservation of biometrics have focus on the NIST's study. Finally, facial and iris recognition will be examined base on cases and examples. Iris recognition has found to be more benefit then the facial recognition.

History of Biometrics

The first known example of biometrics in practice was a form of finger printing being used in china in the 14th century, as reported by explorer Joao de Barros (Grafinkel 2000). He noted down that the Chinese merchants were stamping children's palm prints and footprints on paper with ink to distinguish the young children from one another (Grafinkel 2000). This is one of the earliest known cases of biometrics in use and is still being used today. In 1890's, an anthropologist named Alphonse Bertillon sought to fix the problem of identifying convicted criminals and turned biometrics into a distinct field of study (Garfinkel 2000). His development of "Bertillonage", a method of multiple body measurements that was used by police authorities throughout the world, until it quickly faded when it was discovered that some people shared the same measurements. (Garfinkel 2000). He also found that based on the measurements alone, two people could get treated as one. (Grafinkel 2000).

After the failure of Bertillonage, the finger printing is used in Scotland Yard by the police to identify and track the criminals. Following that, Francis Francis Galton has tried to improve the Bertillon system proposed various biometric indices for facial profiles and he established an Anthropometric Laboratory (Tolba, El-Baz & El-Harby). Consequently, many facial measurements have been developed (Samal & Iyengar 1992). As technology gets more and more advanced, the ways to distinguish the different biometric identification become more and more precise.

What is Biometrics-Substantive Science

Biometrics is the science and technology of authentication which establishing the identity of an individual by measuring the person's physiological or behavioural features (Woodward 2001). Since early in the 20th century its substantive science was referred to "the field of development of statistical and mathematical methods applicable to data analysis problems in the biological sciences" (Nadel 2004, p. 21). Forensic biology involves the application of criminalities in cases where biological materials may be present, and also primary purpose of a forensic system is to identify suspects based upon latent images taken from a crime scene (Jain, Pankanti & Prabhakar 2003).

Daugman (2003, p. 281) has claimed that empirical and mathematical models are validated by comparing their statistical distributions from real biometrics and has published treatments addressing the statistical uniqueness of the human iris. For instance, Maio et al. (2002, p. 30812-13) revealed that the closest testing that approaches what is needed to validate synthetic biometrics generators against real biometrics is the University of Bologna Fingerprint Verification Competition (FVC) Tests. These tests used synthetic images from the University of Bologna's SFinGe tool and result given was very realistic images simulate a low-cost sensor with rotation, displacement and distortion characteristics approximating images from real biometrics (Maio et al 2002).

Biometric Systems

Biometric systems have two purposes: identification and authentication/ verification (Jain, Pankanti & Prabhakar 2003). Biometrics applies to both a pre-event and post-event situation such as gaining access, surveillance, or verification (Oliver 1999). Biometric identification technologies use a particular biological aspect of the human body to recognize or confirm that person's identity (Jain, Pankanti & Prabhakar 2003). These technologies can be applied in the criminal justice system to enhance access control and identity verification in correctional facilities, and as an investigative tool for identifying missing and exploited children as well as criminals captured by surveillance systems (Woodward 2001). This led to recent advancements in biometrics sensors and matching algorithms have led to the deployment of biometric authentication in a large number of civilian applications (Gerats & Ruifrok 2003).

In addition, a biometric system's accuracy requirements depend greatly on the application (Jain, Pankanti & Prabhakar 2003). For example, in some forensic applications, such as criminal identification, false non-match rate (FNMR) is the critical design issue to avoid overlook of a criminal even at the risk of manually examining a large number of potentially incorrect matches that the biometric system identifies (Jain, Pankanti & Prabhakar 2003). On the other extreme, false match rate (FMR) might be one of the most important factors in a highly secure access-control application, where the primary objective is deterring fraud (Jain, Pankanti & Prabhakar 2003)

Forensic Application

Forensic applications have relied on human experts to match biometric features such as corpse identification, criminal investigation, terrorist identification, parenthood determination, and missing children (Jain, Pankanti & Prabhakar 2003). Jain et al. (2004) stated that the government and forensic category consist of "mainly negative-recognition applications that require identification such as background checking of employees and preventing terrorists from boarding airplanes, must perform personal recognition in identification mode" (pp. 36-40). In this section of the paper, terrorist identification will be examined base on an example.

Terrorist Identification:

The Visionics' CEO announced that its system, FaceIt facial recognition, captures the images of faces taken from security cameras in airports and creates a unique mathematical identifier called a "face print" for each face. (Woodward 2001). The face print is compared to those already stored in the