Hand
Recognition
One of the first practical biometric based personal identification (PI) systems used hand geometry [1][2]. As the name suggests, a hand geometry system measures the physical geometric characteristics of a user's fingers and hand. The prevailing hand geometry technology uses a digital camera to capture silhouette images of the top and side of the hand. Several geometric measurements of the user's hand are computed from these images. No surface detail (as in fingerprints) is considered in the hand geometry system measurements.
Although hand geometry based PI systems have enjoyed many successes over the past twenty to twenty-five years, there is still debate over the "uniqueness" and "permanence" characteristics of the geometry of the hand as a biometric. From a uniqueness standpoint, some biometric "experts" feel that the geometry of the human hand is not rich in discriminative features such as fingerprints and irises [2]. This might make hand geometry a poor candidate for "identification mode" operation if there were a large database of enrollees. From a permanence standpoint, the geometry of the human hand is not necessarily stable over one's lifespan although most changes are insidious. Changes include aging, disease (arthritis can be extremely disfiguring), and injury (non-insidious change). The predominant hand geometry technology accounts for insidious instabilities by updating (averaging) a user's template with each successive scan (identity verification) [2].
Hand geometry based PI is one of the better-established biometric technologies. While it is primarily a "verification mode" technology, it offers a good balance of performance and ease of use. The technology requires hand contact and is considered invasive by some users. Using the system in "verification mode" manages the biometric "uniqueness" characteristic deficiency, while template averaging overcomes its "permanence" characteristic shortcoming. Thousands of hand geometry scanners are deployed around the world and are predominantly used in a wide range of physical access control and time and attendance monitoring applications. The hand scanner's ease of use help to make users more comfortable with and accepting of the technology. Other advantages include small template size and speed of operation. However, if user "identification mode" is a PI system requirement, one may need to consider other technologies.
[1] Julian Ashbourn, "Biometrics: Advanced Identity Verification, The Complete Guide," Springer, London, 2000.[2] A. Jain, R. Bolle, S. Pankanti, editors, "BIOMETRICS Personal Identification in Networked Society," Kluwer Academic Press, Boston, 1999.