Handwritten signature verification by using a six-axis motion sensor and SVM

Chang-Chieh Cheng; Yi Chi Chen; Yu-Tai Ching

doi:10.1145/3341162.3343840

Handwritten signature verification by using a six-axis motion sensor and SVM

Chang-Chieh Cheng^*, Yi Chi Chen, Yu-Tai Ching

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Signature verification, if we consider the muscle memory, is a biometric for identification technology. To access muscle memory, we use a motion sensor that consists of accelerometer and gyroscope to implement a signature verification system. The motion sensor records six motion values including three-axis accelerations and angular velocities while name signing. 14 features of signature are extracted from the sequence of accelerations and angular velocities. A support vector machine (SVM) is then applied to verify the signatures. The proposed method was applied to verify the Chinese signatures. The SVM is trained by the training data from each person. The true positive rate of the proposed method can reach to 95.66%. Fake signatures generated by tracing from true signatures can also be recognized by the proposed method.

Original language	American English
Title of host publication	UbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers
Publisher	Association for Computing Machinery, Inc
Pages	25-28
Number of pages	4
ISBN (Electronic)	9781450368698
DOIs	https://doi.org/10.1145/3341162.3343840
State	Published - 9 Sep 2019
Event	2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and 2019 ACM International Symposium on Wearable Computers, UbiComp/ISWC 2019 - London, United Kingdom Duration: 9 Sep 2019 → 13 Sep 2019

Publication series

Name	UbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers

Conference

Conference	2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and 2019 ACM International Symposium on Wearable Computers, UbiComp/ISWC 2019
Country/Territory	United Kingdom
City	London
Period	9/09/19 → 13/09/19

Keywords

Handwritten signature verification
Machine learning
Motion sensor
SVM

Access to Document

10.1145/3341162.3343840

Cite this

Cheng, C.-C., Chen, Y. C., & Ching, Y.-T. (2019). Handwritten signature verification by using a six-axis motion sensor and SVM. In UbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers (pp. 25-28). (UbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers). Association for Computing Machinery, Inc. https://doi.org/10.1145/3341162.3343840

Cheng, Chang-Chieh ; Chen, Yi Chi ; Ching, Yu-Tai. / Handwritten signature verification by using a six-axis motion sensor and SVM. UbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers. Association for Computing Machinery, Inc, 2019. pp. 25-28 (UbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers).

@inproceedings{f3e9bc59d0a7449ea4f389e7a5acc286,

title = "Handwritten signature verification by using a six-axis motion sensor and SVM",

abstract = "Signature verification, if we consider the muscle memory, is a biometric for identification technology. To access muscle memory, we use a motion sensor that consists of accelerometer and gyroscope to implement a signature verification system. The motion sensor records six motion values including three-axis accelerations and angular velocities while name signing. 14 features of signature are extracted from the sequence of accelerations and angular velocities. A support vector machine (SVM) is then applied to verify the signatures. The proposed method was applied to verify the Chinese signatures. The SVM is trained by the training data from each person. The true positive rate of the proposed method can reach to 95.66%. Fake signatures generated by tracing from true signatures can also be recognized by the proposed method.",

keywords = "Handwritten signature verification, Machine learning, Motion sensor, SVM",

author = "Chang-Chieh Cheng and Chen, {Yi Chi} and Yu-Tai Ching",

note = "Publisher Copyright: {\textcopyright} 2019 Copyright held by the owner/author(s). Publication rights licensed to ACM.; 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and 2019 ACM International Symposium on Wearable Computers, UbiComp/ISWC 2019 ; Conference date: 09-09-2019 Through 13-09-2019",

year = "2019",

month = sep,

day = "9",

doi = "10.1145/3341162.3343840",

language = "American English",

series = "UbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers",

publisher = "Association for Computing Machinery, Inc",

pages = "25--28",

booktitle = "UbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers",

}

Cheng, C-C, Chen, YC & Ching, Y-T 2019, Handwritten signature verification by using a six-axis motion sensor and SVM. in UbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers. UbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers, Association for Computing Machinery, Inc, pp. 25-28, 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and 2019 ACM International Symposium on Wearable Computers, UbiComp/ISWC 2019, London, United Kingdom, 9/09/19. https://doi.org/10.1145/3341162.3343840

Handwritten signature verification by using a six-axis motion sensor and SVM. / Cheng, Chang-Chieh; Chen, Yi Chi; Ching, Yu-Tai.
UbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers. Association for Computing Machinery, Inc, 2019. p. 25-28 (UbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Handwritten signature verification by using a six-axis motion sensor and SVM

AU - Cheng, Chang-Chieh

AU - Chen, Yi Chi

AU - Ching, Yu-Tai

PY - 2019/9/9

Y1 - 2019/9/9

N2 - Signature verification, if we consider the muscle memory, is a biometric for identification technology. To access muscle memory, we use a motion sensor that consists of accelerometer and gyroscope to implement a signature verification system. The motion sensor records six motion values including three-axis accelerations and angular velocities while name signing. 14 features of signature are extracted from the sequence of accelerations and angular velocities. A support vector machine (SVM) is then applied to verify the signatures. The proposed method was applied to verify the Chinese signatures. The SVM is trained by the training data from each person. The true positive rate of the proposed method can reach to 95.66%. Fake signatures generated by tracing from true signatures can also be recognized by the proposed method.

AB - Signature verification, if we consider the muscle memory, is a biometric for identification technology. To access muscle memory, we use a motion sensor that consists of accelerometer and gyroscope to implement a signature verification system. The motion sensor records six motion values including three-axis accelerations and angular velocities while name signing. 14 features of signature are extracted from the sequence of accelerations and angular velocities. A support vector machine (SVM) is then applied to verify the signatures. The proposed method was applied to verify the Chinese signatures. The SVM is trained by the training data from each person. The true positive rate of the proposed method can reach to 95.66%. Fake signatures generated by tracing from true signatures can also be recognized by the proposed method.

KW - Handwritten signature verification

KW - Machine learning

KW - Motion sensor

KW - SVM

UR - http://www.scopus.com/inward/record.url?scp=85072888877&partnerID=8YFLogxK

U2 - 10.1145/3341162.3343840

DO - 10.1145/3341162.3343840

M3 - Conference contribution

AN - SCOPUS:85072888877

T3 - UbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers

SP - 25

EP - 28

BT - UbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers

PB - Association for Computing Machinery, Inc

T2 - 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and 2019 ACM International Symposium on Wearable Computers, UbiComp/ISWC 2019

Y2 - 9 September 2019 through 13 September 2019

ER -

Cheng CC, Chen YC, Ching YT. Handwritten signature verification by using a six-axis motion sensor and SVM. In UbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers. Association for Computing Machinery, Inc. 2019. p. 25-28. (UbiComp/ISWC 2019- - Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers). doi: 10.1145/3341162.3343840

Handwritten signature verification by using a six-axis motion sensor and SVM

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this