Publication:
A novel architecture to verify offline hand-written signatures using convolutional neural network

Simple item page
dc.citedby2
dc.contributor.authorAlkaabi S.en_US
dc.contributor.authorYussof S.en_US
dc.contributor.authorAlmulla S.en_US
dc.contributor.authorAl-Khateeb H.en_US
dc.contributor.authorAlabdulsalam A.A.en_US
dc.contributor.authorid57212311690en_US
dc.contributor.authorid16023225600en_US
dc.contributor.authorid36473139200en_US
dc.contributor.authorid55339456900en_US
dc.contributor.authorid57219701686en_US
dc.date.accessioned2023-05-29T07:23:46Z
dc.date.available2023-05-29T07:23:46Z
dc.date.issued2019
dc.descriptionAuthentication; Convolution; Neural networks; Verification; Convolutional neural network; Data augmentation; Forensics; Handwritten signatures; Signature verification; Network architectureen_US
dc.description.abstractHand-written signatures are marked on documents to establish legally binding evidence of identity and intent. However, they are prone to forgery, and the design of an accurate feature extractor to distinguish between highly-skilled forgeries and genuine signatures is a challenging task. In this paper, we propose a Convolution Neural Network (CNN) architecture for Signature Verification (SV). The algorithm is trained using two signatures, genuine and forged. Then the SV module performs a classification task to determine if any two signatures are of the same individual or not. The simulation results show that the proposed method can achieve 27% (relatively) better results than the benchmark scheme. The paper also integrated different data augmentation techniques for the signature data, which further improved the efficiency of the proposed method by 14% (relative). � 2019 IEEE.en_US
dc.description.natureFinalen_US
dc.identifier.ArtNo8910275
dc.identifier.doi10.1109/3ICT.2019.8910275
dc.identifier.scopus2-s2.0-85076434875
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85076434875&doi=10.1109%2f3ICT.2019.8910275&partnerID=40&md5=239e1a66de5aaae0d64d6436ce7011a5
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/24468
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.sourceScopus
dc.sourcetitle2019 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2019
dc.titleA novel architecture to verify offline hand-written signatures using convolutional neural networken_US
dc.typeConference Paperen_US
dspace.entity.typePublication
Files
Collections
SCOPUS