%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2015/07.22.22.37
%2 sid.inpe.br/sibgrapi/2015/07.22.22.37.19
%T Uma abordagem para detecção de lentes de contato baseado em Deep Representations
%D 2015
%A Silva, Pedro Henrique,
%A Menotti, David,
%E Vieira, Thales Miranda de Almeida,
%E Mello, Vinicius Moreira,
%B Conference on Graphics, Patterns and Images, 28 (SIBGRAPI)
%C Salvador, BA, Brazil
%8 26-29 Aug. 2015
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K Íris, Detecção de Lentes de Contato, Aprendizado em Profundidade, Redes Convolucionais.
%X Spoofing detection is a challenging task in biometric systems, when differentiating illegitimate users from genuine ones. Although iris scans are far more inclusive than fingerprints, and also more precise for person authentication, iris recognition systems are vulnerable to spoofing via textured cosmetic contact lenses. Iris spoofing detection is also referred to as liveness detection (binary classification of fake and real images). In this work, we focus on a three-class detection problem: images with textured (colored) contact lenses, soft contact lenses, and no lenses. Our approach uses a convolutional network to build a deep image representation and an additional fully-connected single layer with softmax regression for classification. Experiments are conducted in comparison with a state-of-the-art approach (SOTA) on two public iris image databases for contact lens detection: 2013 Notre Dame and IIIT-Delhi. The results show that our approach can achieve better results than SOTA on the former database and comparable results on the latter. Despite the proposed approach does not segment iris images, the results for the IIIT-Delhi base reaches values comparable to the SOTA, which segments the images. Taking this into account, we conclude that the results are promising.
%@language pt
%3 2015-SIBGRAPI-ContactLenses.pdf