ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

Mathematical Context of Recurrent Line Tracking Enhancement Algorithm in Fingervein Technology

Journal: International Research Journal of Advanced Engineering and Science (IRJAES) (Vol.3, No. 3)

Publication Date:

Authors : ;

Page : 184-187

Keywords : Biometrics; Algorithm; Fingervein technology; Physiological characteristics; and Recurrent line tracking.;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

Biometrics based technology varies from one system to another. Using human physiological characteristics such as fingerprints, iris, fingervein, face shape, hand geometry and so on for identification has been a long time effort made to improve on the security of personal identification system. But most of these systems have their limitations. Conventional methods for extracting lineshaped features from images include the matched-filter method, mathematical morphology, connection of emphasized edge lines, and ridge line following for minutiae detection in gray scale fingerprint images. The matched-filter and morphological methods for example, can execute fast feature extraction because all that's required is to filter the image. However, this can also emphasize irregular shading, which presents an obstacle to personal identification since this obscures parts of the pattern of veins. Moreover, dots of noise are also emphasized because continuity is not considered. When the connection of emphasized edge lines is used to extract a fingervein pattern, line extraction can be executed if one takes into account continuity. However, the differential operation and optimization of the line connections carry immense computational costs. It may take ten or more minutes to process an image. Therefore, this method is not suitable when real-time processing is required. The minutiae detection algorithm is based on ridge line following. The ridge line following, which is executed by checking the local darkest position in the cross-sectional profiles, works well if the ridge appears clearly. However, fingervein images are not clear enough for this method to be used. Fingervein pattern is characterized not only by the vein blood vessel pattern but also by the irregular shading produced by the various thicknesses of the finger bones and muscles captured under infrared light. The captured images contain not only vein patterns but also irregular shading and noise. For a robust line extraction, this paper presents the mathematical context of recurrent line tracking enhancement algorithm in fingervein technology over conventional methods for reliable, efficient and effective personal identification system.

Last modified: 2018-09-22 23:24:41