Close
Metadata

%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2018/10.26.22.53
%2 sid.inpe.br/sibgrapi/2018/10.26.22.53.20
%T Estudo comparativo sobre o uso de pré-processamento na detecção de poros de suor em impressões digitais
%D 2018
%8 Oct. 29 - Nov. 1, 2018
%A Rodrigues, Emily S.,
%A Borges, Vinicius R. P.,
%@affiliation Universidade de Brasília
%@affiliation Universidade de Brasília
%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
%S Proceedings
%I Sociedade Brasileira de Computação
%J Porto Alegre
%K biometria, impressão digital, poros de suor, processamento de imagem, pré-processamento.
%X This paper describes a study regarding the use of image preprocessing techniques to improve the quality of fingerprints in digital images. We investigated and compared some low-pass filtering (Gaussian, median and anisotropic diffusion filtering) and contrast enhancement (histogram equalization and image normalization) techniques for identifying and extracting pores in high resolution images. Our study was conducted by using an automatic methodology for pore extraction in high resolution fingerprint images, in which we considered several combinations of filtering and contrast enhancement methods. Experiments were performed using a public fingerprint image set and compared the true pore and false pore detection rates of those combinations in relation to the ground-truth images. The results reported that the combination image normalization alongside anisotropic diffusion filtering yielded the best performance.
%@language pt
%3 SIBGRAPI2018.pdf


Close