@InProceedings{LimaBati:2018:SeImÍr,
author = "Lima, Diego Filipe Souza de and Batista, Leonardo Vidal",
affiliation = "{Federal University of Para{\'{\i}}ba} and {Federal University
of Para{\'{\i}}ba}",
title = "Segmenta{\c{c}}{\~a}o de Imagens de {\'{\I}}ris Utilizando
Deep Learning",
booktitle = "Proceedings...",
year = "2018",
editor = "Ross, Arun and Gastal, Eduardo S. L. and Jorge, Joaquim A. and
Queiroz, Ricardo L. de and Minetto, Rodrigo and Sarkar, Sudeep and
Papa, Jo{\~a}o Paulo and Oliveira, Manuel M. and Arbel{\'a}ez,
Pablo and Mery, Domingo and Oliveira, Maria Cristina Ferreira de
and Spina, Thiago Vallin and Mendes, Caroline Mazetto and Costa,
Henrique S{\'e}rgio Gutierrez and Mejail, Marta Estela and Geus,
Klaus de and Scheer, Sergio",
organization = "Conference on Graphics, Patterns and Images, 31. (SIBGRAPI)",
publisher = "Sociedade Brasileira de Computa{\c{c}}{\~a}o",
address = "Porto Alegre",
keywords = "{\'{\I}}ris, Segmenta{\c{c}}{\~a}o, Deep Learning,
Autoencoder.",
abstract = "Current biometric systems can recognize individuals through
various trait such as fingerprint, face, iris, palm, etc. Among
these varied characteristics, the iris is one that most needs the
collaboration of the individual. On the other hand, it is one of
the most reliable forms of recognition because of the unique
patterns it has in its composition. However, the use of this trait
in a non-cooperative way means that the current systems perform
below satisfactory, mainly due to the difficulty of locating and
segmenting the iris region, which generates errors that are
propagated throughout the recognition process, affecting the final
performance of the systems directly. The present work proposes an
iris segmentation algorithm using a Deep Learning technique known
as Convolutional Autoencoder, which can perform satisfactorily in
both cooperative and non-cooperative environments. The
satisfactory performance of the algorithm was evident when
compared to algorithms present in the literature, using images
with similar capture patterns. The results of the segmentation
process were evaluated using iris segmentation error and
computational vision metrics, then compared with some of the best
results found in the literature. The proposed method achieved in
some cases an error rate 68% lower than the other algorithms.",
conference-location = "Foz do Igua{\c{c}}u, PR, Brazil",
conference-year = "29 Oct.-1 Nov. 2018",
language = "pt",
ibi = "8JMKD3MGPAW/3S4EE6B",
url = "http://urlib.net/ibi/8JMKD3MGPAW/3S4EE6B",
targetfile = "Segmenta{\c{c}}{\~a}o de Imagens de {\'{\I}}ris Utilizando
Deep Learning.pdf",
urlaccessdate = "2024, Apr. 29"
}