An Approach for Hand Vein Representation and Indexing

An Approach for Hand Vein Representation and Indexing

D S. Guru (University of Mysore, India), K B. Nagasundara (University of Mysore, India), S Manjunath (University of Mysore, India) and R Dinesh (LG Soft India Limited, India)
Copyright: © 2011 |Pages: 15
DOI: 10.4018/jdcf.2011040101
OnDemand PDF Download:
No Current Special Offers


This paper proposes a model for representing and indexing of hand vein images. The proposed representation model identifies the junction points and perceives the spatial relationships existing among all junction points in hand vein images by the use of triangular spatial relationship (TSR). The model preserves the TSR among the junction points in a symbolic hand vein image by the use of quadruples and for each quadruple, a unique TSR key is generated. A novel methodology to label the junction points based on graph properties of junction points is also proposed. A Symbolic Hand Vein Image Database (SHVID) is created through the construction of B-tree, an efficient multilevel indexing structure. A methodology to retrieve similar symbolic hand vein images for a given query image is also presented. The proposed methodology has shown promising results.
Article Preview


In today’s networked society, there are increasing number of situations, which require an individual as a user to be recognized electronically. The area of identity recognition has been receiving a greater attention from a biometric research community. There is an increasing demand of reliable automatic identity recognition systems for forensic, civilian, and commercial applications like criminal investigation, welfare disbursement, border crossing, automatic teller machine and access control. Conventional methods based on passwords and cards have a certain number of drawbacks. Passwords may be forgotten or shared. Cards may be lost, misplaced or even be stolen, then a system is not able to make the difference between genuine user and an imposter. Instead of these passwords and cards, a lot of techniques have been investigated to recognize users by biological characteristics which are difficult to forge (Jain et al., 2000).

Biometrics is the area related to recognition of a person by means of physiological and/or behavioral characteristics of the person. The most common physiological and behavioral characteristics of an individual which are being used for automatic recognition are, to name a few, fingerprint, face, iris, palm print, vein pattern, hand geometry, signature (Maltoni et al., 2003; Maiorana et al., 2009).

Because of the importance of biometric, many researchers have been working towards development of biometric systems. The biometric systems have four basic modules (Ross & Jain, 2003): sensor module, feature extraction module, matching module and decision module. In sensor module, the corresponding biometric characteristics are captured. A set of discriminative features is extracted in feature extraction module. The matching module compares this feature set with the template set present in the database and generates a matching score. In the decision module, the user’s identity is established based on the matching score.

Nowadays, there are many types of biometric systems commercially available such as fingerprints, iris/retina and hand shape devices. Each of these systems has its own merits and demerits. In case of fingerprints, direct contact of the finger with the fingerprint image extracting sensor causes degradation in performance, especially in factory construction sites where good-quality fingerprints are hard to obtain due to oil from the finger, moisture, dirt, etc. Secondly the fingerprint recognition is easy to duplicate and imitate, because the fingerprint is the surface character of a body (Ding et al., 2005). In the case of iris/retina scanners, users must place the eye closer to the scanner, causing an uncomfortable feeling or privacy-infringing feeling (Xueyan et al., 2007). In case of hand-shape recognizers, problems may arise with users who suffer from arthritis or rheumatism, so they are rarely used due to their poor performance. On the other hand, hand vein biometric overcomes the above mentioned disadvantages. Vein pattern is the vast network of blood vessels underneath a person’s skin and vein patterns are much harder for intruders to copy compared to other biometric features. The properties of uniqueness, stability and strong immunity to forgery of the vein pattern make it a potentially good biometric that offers secure and reliable features for person identification.

A hand vein recognition system has the following advantages compared to other biometric systems such as fingerprint, iris, face, and so on (Wang et al., 2007).

Complete Article List

Search this Journal:
Volume 14: 2 Issues (2022)
Volume 13: 6 Issues (2021)
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing