An Offline Signature Verification and Forgery Detection Method Based on a Single Known Sample and an Explainable Deep Learning Approach

Autor: Hsin-Hsiung Kao, Che-Yen Wen
Jazyk: angličtina
Rok vydání: 2020
Předmět:
Biometrics
explainable deep learning
Computer science
forensic science
Feature extraction
Sample (statistics)
02 engineering and technology
Cashier's check
Convolutional neural network
lcsh:Technology
lcsh:Chemistry
020204 information systems
0202 electrical engineering
electronic engineering
information engineering
General Materials Science
Instrumentation
lcsh:QH301-705.5
Fluid Flow and Transfer Processes
convolutional neural network (CNN)
business.industry
lcsh:T
Process Chemistry and Technology
Deep learning
handwritten signature verification
General Engineering
signature examination
Pattern recognition
Signature (logic)
lcsh:QC1-999
Computer Science Applications
Identification (information)
lcsh:Biology (General)
lcsh:QD1-999
lcsh:TA1-2040
020201 artificial intelligence & image processing
Artificial intelligence
business
lcsh:Engineering (General). Civil engineering (General)
lcsh:Physics
Zdroj: Applied Sciences
Volume 10
Issue 11
Applied Sciences, Vol 10, Iss 3716, p 3716 (2020)
ISSN: 2076-3417
DOI: 10.3390/app10113716
Popis: Signature verification is one of the biometric techniques frequently used for personal identification. In many commercial scenarios, such as bank check payment, the signature verification process is based on human examination of a single known sample. Although there is extensive research on automatic signature verification, yet few attempts have been made to perform the verification based on a single reference sample. In this paper, we propose an off-line handwritten signature verification method based on an explainable deep learning method (deep convolutional neural network, DCNN) and unique local feature extraction approach. We use the open-source dataset, Document Analysis and Recognition (ICDAR) 2011 SigComp, to train our system and verify a questioned signature as genuine or a forgery. All samples used in our testing process are collected from a new author whose signatures are not present in the training or other stages. From the experimental results, we get the accuracy between 94.37% and 99.96%, false rejection rate (FRR) between 5.88% and 0%, false acceptance rate (FAR) between 0.22% and 5.34% in our testing dataset.
Databáze: OpenAIRE
Externí odkaz: