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
Sistem pengesahan cap jari digunakan secara meluas dalam peranti mudah alih kerana ciri tersendiri cap jari dan kemudahan penangkapan. Biasanya, peranti mudah alih menggunakan penderia kecil, yang mempunyai kawasan terhad, untuk menangkap cap jari. Sementara itu, kaedah pengekstrakan ciri cap jari konvensional memerlukan maklumat cap jari yang terperinci, yang tidak sesuai untuk penderia kecil tersebut. Makalah ini mencadangkan kaedah pengesahan cap jari baru untuk penderia kawasan kecil berdasarkan pembelajaran mendalam. Kaedah sistematik menggabungkan rangkaian neural convolutional dalam (DCNN) dalam rangkaian Siam untuk pengekstrakan ciri dan XGBoost untuk latihan persamaan cap jari. Selain itu, teknik pelapik juga diperkenalkan untuk mengelakkan masalah ralat pembalut. Keputusan eksperimen menunjukkan bahawa kaedah tersebut mencapai ketepatan yang lebih baik sebanyak 66.6% dan 22.6% dalam dataset FingerPassDB7 dan FVC2006DB1B, masing-masing, berbanding kaedah sedia ada.
Nabilah SHABRINA
Tokyo Institute of Technology
Dongju LI
Tokyo Institute of Technology
Tsuyoshi ISSHIKI
Tokyo Institute of Technology
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.
Salinan
Nabilah SHABRINA, Dongju LI, Tsuyoshi ISSHIKI, "High Precision Fingerprint Verification for Small Area Sensor Based on Deep Learning" in IEICE TRANSACTIONS on Fundamentals,
vol. E107-A, no. 1, pp. 157-168, January 2024, doi: 10.1587/transfun.2022EAP1079.
Abstract: The fingerprint verification system is widely used in mobile devices because of fingerprint's distinctive features and ease of capture. Typically, mobile devices utilize small sensors, which have limited area, to capture fingerprint. Meanwhile, conventional fingerprint feature extraction methods need detailed fingerprint information, which is unsuitable for those small sensors. This paper proposes a novel fingerprint verification method for small area sensors based on deep learning. A systematic method combines deep convolutional neural network (DCNN) in a Siamese network for feature extraction and XGBoost for fingerprint similarity training. In addition, a padding technique also introduced to avoid wraparound error problem. Experimental results show that the method achieves an improved accuracy of 66.6% and 22.6% in the FingerPassDB7 and FVC2006DB1B dataset, respectively, compared to the existing methods.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2022EAP1079/_p
Salinan
@ARTICLE{e107-a_1_157,
author={Nabilah SHABRINA, Dongju LI, Tsuyoshi ISSHIKI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={High Precision Fingerprint Verification for Small Area Sensor Based on Deep Learning},
year={2024},
volume={E107-A},
number={1},
pages={157-168},
abstract={The fingerprint verification system is widely used in mobile devices because of fingerprint's distinctive features and ease of capture. Typically, mobile devices utilize small sensors, which have limited area, to capture fingerprint. Meanwhile, conventional fingerprint feature extraction methods need detailed fingerprint information, which is unsuitable for those small sensors. This paper proposes a novel fingerprint verification method for small area sensors based on deep learning. A systematic method combines deep convolutional neural network (DCNN) in a Siamese network for feature extraction and XGBoost for fingerprint similarity training. In addition, a padding technique also introduced to avoid wraparound error problem. Experimental results show that the method achieves an improved accuracy of 66.6% and 22.6% in the FingerPassDB7 and FVC2006DB1B dataset, respectively, compared to the existing methods.},
keywords={},
doi={10.1587/transfun.2022EAP1079},
ISSN={1745-1337},
month={January},}
Salinan
TY - JOUR
TI - High Precision Fingerprint Verification for Small Area Sensor Based on Deep Learning
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 157
EP - 168
AU - Nabilah SHABRINA
AU - Dongju LI
AU - Tsuyoshi ISSHIKI
PY - 2024
DO - 10.1587/transfun.2022EAP1079
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E107-A
IS - 1
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - January 2024
AB - The fingerprint verification system is widely used in mobile devices because of fingerprint's distinctive features and ease of capture. Typically, mobile devices utilize small sensors, which have limited area, to capture fingerprint. Meanwhile, conventional fingerprint feature extraction methods need detailed fingerprint information, which is unsuitable for those small sensors. This paper proposes a novel fingerprint verification method for small area sensors based on deep learning. A systematic method combines deep convolutional neural network (DCNN) in a Siamese network for feature extraction and XGBoost for fingerprint similarity training. In addition, a padding technique also introduced to avoid wraparound error problem. Experimental results show that the method achieves an improved accuracy of 66.6% and 22.6% in the FingerPassDB7 and FVC2006DB1B dataset, respectively, compared to the existing methods.
ER -