The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
É teoricamente impossível restaurar a imagem original da impressão digital a partir de uma sequência de imagens lineares capturadas por um sensor de linha. No entanto, neste artigo propomos um algoritmo único de geração de imagens de impressões digitais, que deriva imagens de impressões digitais a partir de sequências de imagens de linhas capturadas em diferentes velocidades de furto pelo sensor de linha. Uma representação de imagem contínua, chamada trajetória, é usada na modelagem da distorção de imagens brutas de impressões digitais. Sequências de imagens de linha capturadas do mesmo dedo são consideradas sequências de pontos, que são amostrados na mesma trajetória no espaço vetorial N-dimensional. O ponto chave aqui não é reconstruir a imagem original, mas gerar imagens idênticas a partir da trajetória, que são independentes da velocidade do dedo. O método para aplicação do algoritmo em uma aplicação prática também é apresentado. Resultados experimentais em um banco de dados de imagens brutas de impressões digitais de um sensor de linha mostram que as imagens de impressões digitais geradas são independentes da velocidade do furto e podem alcançar um desempenho de correspondência notável com um comparador de minúcias convencional.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Hao NI, Dongju LI, Tsuyoshi ISSHIKI, Hiroaki KUNIEDA, "Unique Fingerprint-Image-Generation Algorithm for Line Sensors" in IEICE TRANSACTIONS on Fundamentals,
vol. E94-A, no. 2, pp. 781-788, February 2011, doi: 10.1587/transfun.E94.A.781.
Abstract: It is theoretically impossible to restore the original fingerprint image from a sequence of line images captured by a line sensor. However, in this paper we propose a unique fingerprint-image-generation algorithm, which derives fingerprint images from sequences of line images captured at different swipe speeds by the line sensor. A continuous image representation, called trajectory, is used in modeling distortion of raw fingerprint images. Sequences of line images captured from the same finger are considered as sequences of points, which are sampled on the same trajectory in N-dimensional vector space. The key point here is not to reconstruct the original image, but to generate identical images from the trajectory, which are independent of the swipe speed of the finger. The method for applying the algorithm in a practical application is also presented. Experimental results on a raw fingerprint image database from a line sensor show that the generated fingerprint images are independent of swipe speed, and can achieve remarkable matching performance with a conventional minutiae matcher.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E94.A.781/_p
Copiar
@ARTICLE{e94-a_2_781,
author={Hao NI, Dongju LI, Tsuyoshi ISSHIKI, Hiroaki KUNIEDA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Unique Fingerprint-Image-Generation Algorithm for Line Sensors},
year={2011},
volume={E94-A},
number={2},
pages={781-788},
abstract={It is theoretically impossible to restore the original fingerprint image from a sequence of line images captured by a line sensor. However, in this paper we propose a unique fingerprint-image-generation algorithm, which derives fingerprint images from sequences of line images captured at different swipe speeds by the line sensor. A continuous image representation, called trajectory, is used in modeling distortion of raw fingerprint images. Sequences of line images captured from the same finger are considered as sequences of points, which are sampled on the same trajectory in N-dimensional vector space. The key point here is not to reconstruct the original image, but to generate identical images from the trajectory, which are independent of the swipe speed of the finger. The method for applying the algorithm in a practical application is also presented. Experimental results on a raw fingerprint image database from a line sensor show that the generated fingerprint images are independent of swipe speed, and can achieve remarkable matching performance with a conventional minutiae matcher.},
keywords={},
doi={10.1587/transfun.E94.A.781},
ISSN={1745-1337},
month={February},}
Copiar
TY - JOUR
TI - Unique Fingerprint-Image-Generation Algorithm for Line Sensors
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 781
EP - 788
AU - Hao NI
AU - Dongju LI
AU - Tsuyoshi ISSHIKI
AU - Hiroaki KUNIEDA
PY - 2011
DO - 10.1587/transfun.E94.A.781
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E94-A
IS - 2
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - February 2011
AB - It is theoretically impossible to restore the original fingerprint image from a sequence of line images captured by a line sensor. However, in this paper we propose a unique fingerprint-image-generation algorithm, which derives fingerprint images from sequences of line images captured at different swipe speeds by the line sensor. A continuous image representation, called trajectory, is used in modeling distortion of raw fingerprint images. Sequences of line images captured from the same finger are considered as sequences of points, which are sampled on the same trajectory in N-dimensional vector space. The key point here is not to reconstruct the original image, but to generate identical images from the trajectory, which are independent of the swipe speed of the finger. The method for applying the algorithm in a practical application is also presented. Experimental results on a raw fingerprint image database from a line sensor show that the generated fingerprint images are independent of swipe speed, and can achieve remarkable matching performance with a conventional minutiae matcher.
ER -