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
Nesta pesquisa, propomos um novo método para determinar a vivacidade das impressões digitais para melhorar o comportamento discriminativo e a precisão da classificação dos recursos combinados. Essa abordagem detecta se uma impressão digital provém de uma fonte real ou falsa. Nesta abordagem, as imagens de impressões digitais são analisadas no componente de excitação diferencial (DE) e no componente de padrão binário centralizado (CBP), que produzem a imagem DE e a imagem CBP, respectivamente. As imagens obtidas são utilizadas para gerar um histograma bidimensional que posteriormente é utilizado como vetor de características. Para decidir se uma imagem de impressão digital é de uma fonte real ou falsa, o vetor de recursos é processado usando classificadores de máquina de vetores de suporte (SVM). Para avaliar o desempenho do método proposto e compará-lo com as abordagens existentes, conduzimos experimentos usando os conjuntos de dados da Competição de Detecção de Liveness (LivDet) de 2011 e 2015, coletados de quatro sensores. Os resultados mostram que o método proposto deu resultados comparáveis ou até melhores e provam ainda que os métodos derivados da combinação de características proporcionam um desempenho melhor do que os métodos existentes.
Asera WAYNE ASERA
Kumamoto University
Masayoshi ARITSUGI
Kumamoto University
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
Asera WAYNE ASERA, Masayoshi ARITSUGI, "Weber Centralized Binary Fusion Descriptor for Fingerprint Liveness Detection" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 7, pp. 1422-1425, July 2019, doi: 10.1587/transinf.2019EDL8044.
Abstract: In this research, we propose a novel method to determine fingerprint liveness to improve the discriminative behavior and classification accuracy of the combined features. This approach detects if a fingerprint is from a live or fake source. In this approach, fingerprint images are analyzed in the differential excitation (DE) component and the centralized binary pattern (CBP) component, which yield the DE image and CBP image, respectively. The images obtained are used to generate a two-dimensional histogram that is subsequently used as a feature vector. To decide if a fingerprint image is from a live or fake source, the feature vector is processed using support vector machine (SVM) classifiers. To evaluate the performance of the proposed method and compare it to existing approaches, we conducted experiments using the datasets from the 2011 and 2015 Liveness Detection Competition (LivDet), collected from four sensors. The results show that the proposed method gave comparable or even better results and further prove that methods derived from combination of features provide a better performance than existing methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDL8044/_p
Copiar
@ARTICLE{e102-d_7_1422,
author={Asera WAYNE ASERA, Masayoshi ARITSUGI, },
journal={IEICE TRANSACTIONS on Information},
title={Weber Centralized Binary Fusion Descriptor for Fingerprint Liveness Detection},
year={2019},
volume={E102-D},
number={7},
pages={1422-1425},
abstract={In this research, we propose a novel method to determine fingerprint liveness to improve the discriminative behavior and classification accuracy of the combined features. This approach detects if a fingerprint is from a live or fake source. In this approach, fingerprint images are analyzed in the differential excitation (DE) component and the centralized binary pattern (CBP) component, which yield the DE image and CBP image, respectively. The images obtained are used to generate a two-dimensional histogram that is subsequently used as a feature vector. To decide if a fingerprint image is from a live or fake source, the feature vector is processed using support vector machine (SVM) classifiers. To evaluate the performance of the proposed method and compare it to existing approaches, we conducted experiments using the datasets from the 2011 and 2015 Liveness Detection Competition (LivDet), collected from four sensors. The results show that the proposed method gave comparable or even better results and further prove that methods derived from combination of features provide a better performance than existing methods.},
keywords={},
doi={10.1587/transinf.2019EDL8044},
ISSN={1745-1361},
month={July},}
Copiar
TY - JOUR
TI - Weber Centralized Binary Fusion Descriptor for Fingerprint Liveness Detection
T2 - IEICE TRANSACTIONS on Information
SP - 1422
EP - 1425
AU - Asera WAYNE ASERA
AU - Masayoshi ARITSUGI
PY - 2019
DO - 10.1587/transinf.2019EDL8044
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2019
AB - In this research, we propose a novel method to determine fingerprint liveness to improve the discriminative behavior and classification accuracy of the combined features. This approach detects if a fingerprint is from a live or fake source. In this approach, fingerprint images are analyzed in the differential excitation (DE) component and the centralized binary pattern (CBP) component, which yield the DE image and CBP image, respectively. The images obtained are used to generate a two-dimensional histogram that is subsequently used as a feature vector. To decide if a fingerprint image is from a live or fake source, the feature vector is processed using support vector machine (SVM) classifiers. To evaluate the performance of the proposed method and compare it to existing approaches, we conducted experiments using the datasets from the 2011 and 2015 Liveness Detection Competition (LivDet), collected from four sensors. The results show that the proposed method gave comparable or even better results and further prove that methods derived from combination of features provide a better performance than existing methods.
ER -