Fingerprint Verification based on Gabor Filter Enhancement

Abstract— Human fingerprints are reliable characteristics for personnel identification as it is unique and persistence. A fingerprint pattern consists of ridges, valleys and minutiae. In this paper we propose Fingerprint Verification based on Gabor Filter Enhancement (FVGFE) algorithm for minutiae feature extraction and post processing based on 9-pixel neighborhood. A global feature extraction and fingerprints enhancement are based on Hong enhancement method which is simultaneously able to extract local ridge orientation and ridge frequency. It is observed that the Sensitivity and Specificity values are better compared to the existing algorithms. Keywords-fingerprints; biometrics; ridge; orientation image; minutiae extraction. I.TRODUCTION I N The term Biometrics relates to the measurement (metric) of characteristics of a living (Bio) thing in order to identify a person. Biometric recognition is used as an automatic recognition of individuals based on the physiological or behavioral characteristics. A physiological characteristic such as Fingerprint, Face, Iris, Hand geometry and Retina remains same throughout the lifetime of a person. Behavioral characteristics such as signature, gait, voice and keystroke changes with age and mentality of a person. Fingerprint is one of the most widely used biometric because individuals have tried a number of methods to obliterate or remove their fingerprints by abrading or trying to rub off their fingerprints, burning the fingers, trying to dissolve their fingerprints with strong acids, covering their fingertips with superglue, and even having doctors transplant skin from one finger to another unsuccessfully. The fingerprint is formed in third and fourth month of foetal development and unique with epidermal ridges, furrows and patterns. Distinctiveness and persistence are the highly desirable qualities of fingerprint. Factors such as Skin condition, finger pressure and noise detroit the quality of fingerprint images. The presence of noise gives an image a mottled, grainy, textured or snowy appearance. The images of fingerprint are mistaken during termination; hence it is necessary to investigate the images of fingerprint by using suitable filters. Quality of fingerprint is assessed by Character, Fidelity and Utility. A smoothly flowing pattern formed by alternating crests (ridges) and troughs (valleys) on the palmer aspect of hand is palm print. Formation of a palm print depends on the initial conditions of the embryonic mesoderm from which they develop. The pattern on pulp of each terminal phalanx is considered as an individual pattern and is commonly referred to as a Fingerprint