1 October 2011 Ultrafast fingerprint indexing for embedded systems
Ru Zhou, Sang Woo Sin, Dongju Li, Tsuyoshi Isshiki, Hiroaki Kunieda
Author Affiliations +
Abstract
A novel core-based fingerprint indexing scheme for embedded systems is presented in this paper. Our approach is enabled by our new precise and fast core-detection algorithm with the direction map. It introduces the feature of CMP (core minutiae pair), which describes the coordinates of minutiae and the direction of ridges associated with the minutiae based on the uniquely defined core coordinates. Since each CMP is identical against the shift and rotation of the fingerprint image, the CMP comparison between a template and an input image can be performed without any alignment. The proposed indexing algorithm based on CMP is suitable for embedded systems because the tremendous speed up and the memory reduction are achieved. In fact, the experiments with the fingerprint database FVC2002 show that its speed for the identifications becomes about 40 times faster than conventional approaches, even though the database includes fingerprints with no core.
©(2011) Society of Photo-Optical Instrumentation Engineers (SPIE)
Ru Zhou, Sang Woo Sin, Dongju Li, Tsuyoshi Isshiki, and Hiroaki Kunieda "Ultrafast fingerprint indexing for embedded systems," Optical Engineering 50(10), 107203 (1 October 2011). https://doi.org/10.1117/1.3633336
Published: 1 October 2011
Lens.org Logo
CITATIONS
Cited by 2 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Chemical mechanical planarization

Embedded systems

Databases

Ultrafast phenomena

Image quality

Optical engineering

Feature extraction

RELATED CONTENT


Back to Top