English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/135114
logo share SHARE   Add this article to your Mendeley library MendeleyBASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Exportar a otros formatos:

A Low-Complexity Procedure for Pupil and Iris Detection Suitable for Biometric Identification

AuthorsGayoso Martínez, Víctor; Hernández Álvarez, Fernando; Hernández Encinas, Luis
KeywordsBiometric Identification
Issue Date21-Jul-2014
CitationThe 2014 International Conference on Security and Management (SAM’14), Worldcomp 2014, p.151-157
AbstractThe goal of any biometric system consists in identifying individuals based on a certain characteristic possessed by the persons under examination. Among them, iris recognition is regarded as one of the most reliable and accurate biometric identification systems currently available. Most commercial iris recognition products use patented al- gorithms, which forces open source developers to design and use alternate algorithms. In this contribution, we propose two low-complexity methods for detecting and isolating the pupil and the iris using a greyscale image as the input data. The proposed algorithms can be easily implemented in any device, as they do not use complex operations or image transforms. In addition to that, we show a performance com- parison which includes an implementation of our proposed algorithms and two other open source solutions.
Description7 páginas, 8 figuras, 2 tablas, 6 algoritmos. Comunicación presentada en: The 2014 International Conference on Security and Management (SAM’14), Worldcomp 2014, Las Vegas (USA), 21-24 July 2014.
Publisher version (URL)http://www.worldcomp-proceedings.com/proc/proc2014/sam/SAM_Papers.pdf
Appears in Collections:(ITEFI) Comunicaciones congresos
Files in This Item:
File Description SizeFormat 
Low_complexity_procedure_for_pupil_iris_detection.pdf663,21 kBAdobe PDFThumbnail
Show full item record
Review this work

WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.