Detailed Identification of Fingerprints Using Convolutional Neural Networks

Yahaya Isah Shehu, Ariel Ruiz-Garcia, Vasile Palade, Anne James

Research output: Chapter in Book/Report/Conference proceedingConference proceeding

Abstract

Fingerprints, as one of the most widely used biometric modalities, can be used to identify and distinguish between genders. Gender classification is very important in reducing the time when investigating criminal offenders and gender impersonation. In this work, we use deep Convolutional Neural Networks (CNNs) to not only classify fingerprints by gender, but also identify individual hands and fingers. Transfer learning is employed to speed up the training of the CNN. The CNN achieves an accuracy of 75.2%, 93.5%, and 76.72% for the classification of gender, hand, and fingers, respectively. These results obtained using our publicly available Sokoto Coventry Fingerprint Dataset (SOCOFing) serve as benchmark classification results on this dataset.

Original languageEnglish
Title of host publicationProceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1161-1165
Number of pages5
ISBN (Electronic)978-1-5386-6805-4
ISBN (Print) 978-1-5386-6806-1
DOIs
Publication statusPublished - 17 Jan 2019
Event17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018 - Orlando, United States
Duration: 17 Dec 201820 Dec 2018

Conference

Conference17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018
CountryUnited States
CityOrlando
Period17/12/1820/12/18

Fingerprint

Neural networks
Biometrics

Keywords

  • Convolutional Neural Networks
  • Fingerprints
  • Gender Classification
  • Transfer Learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Safety, Risk, Reliability and Quality
  • Signal Processing
  • Decision Sciences (miscellaneous)

Cite this

Shehu, Y. I., Ruiz-Garcia, A., Palade, V., & James, A. (2019). Detailed Identification of Fingerprints Using Convolutional Neural Networks. In Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018 (pp. 1161-1165). [8614212] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMLA.2018.00187

Detailed Identification of Fingerprints Using Convolutional Neural Networks. / Shehu, Yahaya Isah; Ruiz-Garcia, Ariel; Palade, Vasile; James, Anne.

Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1161-1165 8614212.

Research output: Chapter in Book/Report/Conference proceedingConference proceeding

Shehu, YI, Ruiz-Garcia, A, Palade, V & James, A 2019, Detailed Identification of Fingerprints Using Convolutional Neural Networks. in Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018., 8614212, Institute of Electrical and Electronics Engineers Inc., pp. 1161-1165, 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018, Orlando, United States, 17/12/18. https://doi.org/10.1109/ICMLA.2018.00187
Shehu YI, Ruiz-Garcia A, Palade V, James A. Detailed Identification of Fingerprints Using Convolutional Neural Networks. In Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1161-1165. 8614212 https://doi.org/10.1109/ICMLA.2018.00187
Shehu, Yahaya Isah ; Ruiz-Garcia, Ariel ; Palade, Vasile ; James, Anne. / Detailed Identification of Fingerprints Using Convolutional Neural Networks. Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1161-1165
@inproceedings{0612de1661a245c38427e5ec5e06ed69,
title = "Detailed Identification of Fingerprints Using Convolutional Neural Networks",
abstract = "Fingerprints, as one of the most widely used biometric modalities, can be used to identify and distinguish between genders. Gender classification is very important in reducing the time when investigating criminal offenders and gender impersonation. In this work, we use deep Convolutional Neural Networks (CNNs) to not only classify fingerprints by gender, but also identify individual hands and fingers. Transfer learning is employed to speed up the training of the CNN. The CNN achieves an accuracy of 75.2{\%}, 93.5{\%}, and 76.72{\%} for the classification of gender, hand, and fingers, respectively. These results obtained using our publicly available Sokoto Coventry Fingerprint Dataset (SOCOFing) serve as benchmark classification results on this dataset.",
keywords = "Convolutional Neural Networks, Fingerprints, Gender Classification, Transfer Learning",
author = "Shehu, {Yahaya Isah} and Ariel Ruiz-Garcia and Vasile Palade and Anne James",
year = "2019",
month = "1",
day = "17",
doi = "10.1109/ICMLA.2018.00187",
language = "English",
isbn = "978-1-5386-6806-1",
pages = "1161--1165",
booktitle = "Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Detailed Identification of Fingerprints Using Convolutional Neural Networks

AU - Shehu, Yahaya Isah

AU - Ruiz-Garcia, Ariel

AU - Palade, Vasile

AU - James, Anne

PY - 2019/1/17

Y1 - 2019/1/17

N2 - Fingerprints, as one of the most widely used biometric modalities, can be used to identify and distinguish between genders. Gender classification is very important in reducing the time when investigating criminal offenders and gender impersonation. In this work, we use deep Convolutional Neural Networks (CNNs) to not only classify fingerprints by gender, but also identify individual hands and fingers. Transfer learning is employed to speed up the training of the CNN. The CNN achieves an accuracy of 75.2%, 93.5%, and 76.72% for the classification of gender, hand, and fingers, respectively. These results obtained using our publicly available Sokoto Coventry Fingerprint Dataset (SOCOFing) serve as benchmark classification results on this dataset.

AB - Fingerprints, as one of the most widely used biometric modalities, can be used to identify and distinguish between genders. Gender classification is very important in reducing the time when investigating criminal offenders and gender impersonation. In this work, we use deep Convolutional Neural Networks (CNNs) to not only classify fingerprints by gender, but also identify individual hands and fingers. Transfer learning is employed to speed up the training of the CNN. The CNN achieves an accuracy of 75.2%, 93.5%, and 76.72% for the classification of gender, hand, and fingers, respectively. These results obtained using our publicly available Sokoto Coventry Fingerprint Dataset (SOCOFing) serve as benchmark classification results on this dataset.

KW - Convolutional Neural Networks

KW - Fingerprints

KW - Gender Classification

KW - Transfer Learning

UR - http://www.scopus.com/inward/record.url?scp=85062228219&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2018.00187

DO - 10.1109/ICMLA.2018.00187

M3 - Conference proceeding

SN - 978-1-5386-6806-1

SP - 1161

EP - 1165

BT - Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -