A New Vein Pattern-based Verification System

This paper presents an efficient human recognition system based on vein pattern from the palma dorsa. A new absorption based technique has been proposed to collect good quality images with the help of a low cost camera and light source. The system automatically detects the region of interest from the image and does the necessary preprocessing to extract features. A Euclidean Distance based matching technique has been used for making the decision. It has been tested on a data set of 1750 image samples collected from 341 individuals. The accuracy of the verification system is found to be 99.26% with false rejection rate (FRR) of 0.03%. I. INTRODUCTION Vein pattern of the palma dorsa can be defined as a random 'mesh' of blood carrying tubes. The back of the hand veins are not deeply placed and hence these can be made visible with the help of a good image acquisition system and technique. The geometry of these veins is found to be unique and universal (14). Hence, it can be considered as one of the good human recognition systems. Forensic scientists have always been the biggest reapers of successful biometric systems. User authentication, identity establishment, access control and personal verification etc are a few avenues where forensic scientists employ biometrics. Over time various biometric traits have been used for the above mentioned purposes. Some of them have gained and lost relevance in the course of time. Therefore, constant evolution of existing traits and acceptance of new biometric systems is inevitable. The existing biometric traits, with varying capabilities, have proven successful over the years. Traits like Face, Ear, Iris, Fingerprints, Signatures etc., have dominated the world of biometrics over the years. But each of these biometric traits has its shortcomings. Ear and iris pose a problem during sample collection. Not only is an expensive and highly attended system required for iris but it also has a high failure to enroll rate. In case of ear data, it is hard to capture a non occluded image in real time environment. In case of the most well known face recognition systems there exist some limitations like aging, background, etc (2). Fingerprints, though most reliable, still lack automation and viability as they are also susceptible to wear and aging. Signatures, are liable to forgery. Venal patterns, on the other hand, have the potential to surpass most such problems. Apart from the size of the pattern, the basic geometry always stays the same. Unlike fingerprints, veins are located underneath the skin surface and are not prone to external manipulations. Vein patterns are also almost impossible to replicate because they lie under the skin surface (6).