%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2018/10.23.23.30
%2 sid.inpe.br/sibgrapi/2018/10.23.23.30.09
%T Segmentação de Imagens de Íris Utilizando Deep Learning
%D 2018
%A Lima, Diego Filipe Souza de,
%A Batista, Leonardo Vidal,
%@affiliation Federal University of Paraíba
%@affiliation Federal University of Paraíba
%E Ross, Arun,
%E Gastal, Eduardo S. L.,
%E Jorge, Joaquim A.,
%E Queiroz, Ricardo L. de,
%E Minetto, Rodrigo,
%E Sarkar, Sudeep,
%E Papa, João Paulo,
%E Oliveira, Manuel M.,
%E Arbeláez, Pablo,
%E Mery, Domingo,
%E Oliveira, Maria Cristina Ferreira de,
%E Spina, Thiago Vallin,
%E Mendes, Caroline Mazetto,
%E Costa, Henrique Sérgio Gutierrez,
%E Mejail, Marta Estela,
%E Geus, Klaus de,
%E Scheer, Sergio,
%B Conference on Graphics, Patterns and Images, 31 (SIBGRAPI)
%C Foz do Iguaçu, PR, Brazil
%8 29 Oct.-1 Nov. 2018
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K Íris, Segmentação, Deep Learning, Autoencoder.
%X 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.
%@language pt
%3 Segmentação de Imagens de Íris Utilizando Deep Learning.pdf