Iris Recognition in the Visible Spectrum Based on Eye Image Quality Evaluation

Eduardo Garea Llano, Dailé Osorio Roig, Annette Morales González-Quevedo, Odel Hernández-Hernández

Resumen


Video-based eye image acquisition in the visible spectrum for iris recognition has taken great importance in the current context of the extensive use of video surveillance cameras and mobile devices. This modality can provide more information from the video capture of the eye region, but it is essential that the images captured have a quality that allows an effective recognition process. In this work, an approach for video iris recognition in the visible spectrum is presented. It is based on a scheme whose novelty is in the possibility of evaluating the quality of the eye image simultaneously with the process of video capturing. A measure of image quality that takes into account the elements defined in the ISO / IEC 19794-6 2005 standard and its combination with automatic detection methods is proposed. The experiments developed on two international databases and own video database demonstrate the relevance of the proposal.

 


Palabras clave


Iris Recognition; Quality Measure; Video

Texto completo:

PDF (English)


Facultad de Ingeniería Automática y Biomédica, Universidad Tecnológica de La Habana  José Antonio Echeverría, Cujae, Calle 114 No. 11901. e/ Ciclovía y Rotonda. Marianao 15.
La Habana, Cuba. CP 19390. Telf: (537) 266 3476
E-mail: rielac@tesla.cujae.edu.cu | URL: http://rielac.cujae.edu.cu
ISSN: 1815-5928

Todo el contenido de la revista se encuentra bajo la licencia https://creativecommons.org/licenses/by/4.0/deed.es_ES. La revista en línea tiene acceso abierto y gratuito