Identica Holdings Corporation

data access, Time and Attendance and POS access control

The history of vascular pattern recognition is not long. In 1992 Dr. K. Shimizu published a paper in which he pointed to the potential use of this technology. In the paper he discussed optical trans-body imaging and potential optical CT scanning applications. In 1996 K. Yamamoto and Shimizu presented another paper in which the two discussed research they had undertaken since the earlier paper. The first research paper about the use of vascular patterns for biometric recognition was published in 2000. The paper describes a technology using the subcutaneous blood vessel pattern in the back of the hands - a technology which would come to be called vascular pattern recognition. Additional research has improved the technology, and these improvements led to the commercialization of the technology in a few variant - the back of the hand, finger, and palm- based systems.

How it works

Vascular pattern of the back of the hand: Near-infrared rays generated from a bank of light emitting diodes (LEDs) penetrate the skin of the back of the hand. Owing to the difference in absorbance of blood vessels and other tissues, the reflected near-infrared rays produce an image on the sensor. The image is digitized and processed by image processing techniques producing the extracted vascular pattern. From the extracted vascular pattern, various data — vessel branching points, vessel thickness, and branching angles — are extracted and stored as the template.

Vascular pattern in fingers: Near-infrared rays generated from a bank of LEDs penetrate the finger and are absorbed by the hemoglobin in the blood. The areas in which the rays are absorbed (that is, veins) appear as dark areas similar to a shadow in an image taken by a Charge-Coupled Device (CCD) camera. Image processing can then construct a vein pattern from the captured image. Next this pattern is digitized and compressed so that it can be registered as a template.

How accurate is the technology?

Xin Wang, Kozo Sushita, and Koichi Shimizu examined the accuracy of vein pattern biometrics. For their analysis they used 300 transillumination images (all the pictures in the “How It Works” section are from the article by Wang et al.). They obtained the images of six different