Biometric system

Biometric system is automated recognition of persons based on their biological or/and behavioral characteristics. Automated measurement of biological or/and behavioral characteristics of the person for medical, security or psychological purposes. Depending on the application context, a biometric system may be called either a verification system or an identification system. A verification system verifies a person by comparing the captured biometric characteristic with his own biometric template pre-stored in the system. It conducts the one-to-one comparison to determine whether the identity claimed by the individual is true. A verification system either rejects or accepts the submitted claim of identity. 

An identification system recognizes an individual by searching the entire template database for a match. It conducts one-to-many comparisons to establish the identity of the individual. In an identification system, the system establishes a subject’s identity (or fails if the subject is not enrolled in the system database) without the subject having to claim an identity. Any human physiological and/or behavioral characteristic can be used as a biometric identifier to recognize a person as long as it satisfies these requirements: Universality, which means that each person should have the biometric; Distinctiveness, which indicates that any two persons should be sufficiently different; Permanence, which means that it should be invariant over a period of time; Collectability, which indicates that it can be measured quantitatively. A number of biometric identifiers are in use in various applications. Each biometric has its strengths and weaknesses and the choice typically depends on the application. No single biometric is expected to effectively meet the requirements of all the applications.  In this paper, we will focus on the fingerprint access control application. This type of application can be classified into two verification system or an identification system. The most widely used method for representing a fingerprint is minutiae pattern [15]. The job of minutiae pattern matching is to recognize corresponding minutiae through alignment and pairing. However, it is not easy to extract the minutiae points accurately from the original fingerprint images and the performance of the feature extraction algorithm relies heavily on the quality of the input images. It is essential to implement fingerprint enhancement process before extracting minutiae for the robustness of fingerprint identification algorithm with respect to the quality of fingerprint images. 

Fingerprint enhancement is intended to reduce noises and improve the contrast between ridges and valleys in the gray-scale fingerprint images. Much work has been dedicated to fingerprint enhancement and a variety of relevant approaches have been proposed based on contextual filters, Fourier filtering, Gabor filter, and wavelet [1, 6, 7, 13]. According for these approaches, the Gabor filter-based method achieves comparatively favorable performance and is by far the most popular method for fingerprint enhancement [2, 14]. Access control for restricted areas like airports control area, control room of nuclear applications, and dangerous areas of many application are need reliable authenticated access with high level of security for safety.  So the goal of this work is the development of a biometric access control system for restricted areas based on individual finger print and good enhancement technique like Gabor filter for improvement process of the fingerprint image with acceptable performance. In the first phase of development Matlab can be used to implement algorithms for enhancement process, minutiae extraction and matching processing. Identifying matching fingerprint used based on extracting minutiae for registration stage, verification stage, and identification stage of developed system.