Embedded system for biometric identification based on iris detection

Abstract

Biometric identification provides a reliable and secure user authentication for the increased security requirements. The deployment of advanced computer vision methods for biometric identification system in an embedded platform are severely constrained in their limited processing capabilities, limited memory, limited power source, and algorithms for biometric identification that provide sufficient accuracy tend to be computationally expensive, leading to unacceptable authentication times. This paper describes the design and preliminary implementation of an embedded system for biometric identification based on iris detection (BIOI 2 D). Single Board Computer itself is portable and can be usedfor various purposes such as network based identification system on human face, robot vision platform and embedded web server. In this paper, hardware and software design as well as the experimental result are presented.

Embedded processor optimised for vascular pattern recognition

“…Such systems have traditionally been an important consideration in the design of specific embedded systems. Fingerprint [2], face [3, 4] and iris [5, 6] recognition for embedded systems have been proposed at both commercial and academic levels. Embedded systems are designed under strict energy consumption considerations, in order to limit cost and to provide long‐term performance.…”