{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T19:36:56Z","timestamp":1773862616731,"version":"3.50.1"},"reference-count":30,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000},"content-version":"vor","delay-in-days":76,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Image Processing"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Offline signature verification (OSV) remains a challenging biometric task, particularly under high intra\u2010writer variability and skilled forgery conditions. Most deep learning\u2013based approaches encode reference and query signatures independently, which may limit their ability to model fine\u2010grained correspondences. This paper presents a modified Swin Transformer architecture that introduces an encoder\u2013decoder hierarchy with multi\u2010scale feature aggregation and a pairwise attention mechanism to enable explicit reference\u2013query interaction. The proposed model is trained using a focal contrastive loss under a strict writer\u2010independent protocol. Experiments conducted on the UTSig and CEDAR datasets evaluate performance using accuracy, false acceptance rate, false rejection rate, and equal error rate. Results show consistent reductions in false acceptance rates and modest improvements in overall verification accuracy relative to a Swin Transformer baseline, accompanied by changes in false rejection behaviour. Additional analyses, including learning dynamics, confusion matrices, and threshold sweeps, are used to examine the resulting security\u2013usability trade\u2010offs. These findings suggest that multi\u2010scale cross\u2010attention can contribute to improved discrimination in OSV under challenging variability conditions, while highlighting the importance of careful threshold selection in practical deployments.<\/jats:p>","DOI":"10.1049\/ipr2.70334","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T12:12:49Z","timestamp":1773835969000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Modified Swin Transformer With Pairwise Attention for Offline Signature Verification"],"prefix":"10.1049","volume":"20","author":[{"given":"Wisdom Mawuli Kwodzo","family":"Adzokatse","sequence":"first","affiliation":[{"name":"Department of Computer Science University of Ghana  Accra Ghana"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leonard Mensah","family":"Boante","sequence":"additional","affiliation":[{"name":"Department of Computer Science University of Ghana  Accra Ghana"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benedict","family":"Appati","sequence":"additional","affiliation":[{"name":"Department of Telecommunications Engineering Kwame Nkrumah University of Science &amp; Technology  Kumasi Ghana"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julius Yaw","family":"Ludu","sequence":"additional","affiliation":[{"name":"Department of Computer Science University of Ghana  Accra Ghana"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2798-4524","authenticated-orcid":false,"given":"Justice Kwame","family":"Appati","sequence":"additional","affiliation":[{"name":"Department of Computer Science University of Ghana  Accra Ghana"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"265","published-online":{"date-parts":[[2026,3,18]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPTA.2017.8310112"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2021.116139"},{"key":"e_1_2_10_4_1","first-page":"256","article-title":"Offline Signature Verification Using Rotated Local Binary Pattern (RLBP)","volume":"4","author":"Kiani S. W.","year":"2020","journal-title":"University of Sindh Journal of Information and Communication Technology"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115756"},{"key":"e_1_2_10_6_1","unstructured":"S.Dey A.Dutta J. I.Toledo S. K.Ghosh J.Llados andU.Pal \u201cSigNet: Convolutional Siamese Network for Writer Independent Offline Signature \u201dPattern Recognition Letters(2017): arXiv preprint arXiv:1707.02131 https:\/\/doi.org\/10.48550\/arXiv.1707.02131."},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107851"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2308.01136"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108009"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2022.111312"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109816"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1186\/s42492\u2010022\u201000109\u20100"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/9917246"},{"key":"e_1_2_10_14_1","doi-asserted-by":"crossref","unstructured":"Y. J.XiongandS. Y.Cheng \u201cAttention Based Multiple Siamese Network for Offline Signature Verification \u201d inInternational Conference on Document Analysis and Pattern Recognition(2021) 337\u2013349 https:\/\/doi.org\/10.1007\/978\u20103\u2010030\u201086334\u20100_22.","DOI":"10.1007\/978-3-030-86334-0_22"},{"key":"e_1_2_10_15_1","doi-asserted-by":"crossref","unstructured":"P.Wei H.Li andP.Hu \u201cInverse Discriminative Networks for Handwritten Signature Verification \u201d inIEEE Conference on Computer Vision and Pattern Recognition(2019) https:\/\/doi.org\/10.1109\/CVPR.2019.00591.","DOI":"10.1109\/CVPR.2019.00591"},{"key":"e_1_2_10_16_1","doi-asserted-by":"crossref","unstructured":"A.Foroozandeh A. A.Hemmat andH.Rabbani \u201cOffline Handwritten Signature Verification and Recognition Based on Deep Transfer Learning Using Convolutional Neural Networks (A Literature Review) \u201d in2020 International Conference on Machine Vision and Image Processing(2020) https:\/\/doi.org\/10.1109\/MVIP49855.2020.9187481.","DOI":"10.1109\/MVIP49855.2020.9187481"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109882"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06555-2_22"},{"key":"e_1_2_10_19_1","doi-asserted-by":"crossref","unstructured":"Z.Liu Y.Lin andY.Cao \u201cSwin Transformer: Hierarchical Vision Transformer Using Shifted Windows \u201d inIEEE International Conference on Computer Vision(2021) 10012\u201310022 https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_2_10_20_1","unstructured":"A.Dosovitskiy L.Beyer A.Kolesnikov et\u00a0al. \u201cAn Image is Worth 16\u00d716 Words: Transformers for Image Recognition at Scale \u201d inInternational Conference on Learning Representations 2021 https:\/\/doi.org\/10.48550\/arXiv.2010.11929."},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.03235"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3333681"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105639"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rineng.2025.106425"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/math12172757"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs\u20102533077\/v1"},{"key":"e_1_2_10_27_1","doi-asserted-by":"crossref","unstructured":"F.Vargas M.Ferrer C.Travieso andJ.Alonso \u201cOffline Handwritten Signature GPDS\u2010960 Corpus \u201d inInternational Conference on Document Analysis and Recognition(2007) 764\u2013768 https:\/\/doi.org\/10.1109\/ICDAR.2007.4377018.","DOI":"10.1109\/ICDAR.2007.4377018"},{"key":"e_1_2_10_28_1","unstructured":"P.Khosla P.Teterwak C.Wang et\u00a0al. \u201cSupervised Contrastive Learning \u201d23(2021):1\u201323 https:\/\/doi.org\/10.48550\/arXiv.2004.11362."},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/6672578"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.4018\/IJCINI.286768"},{"key":"e_1_2_10_31_1","doi-asserted-by":"crossref","unstructured":"E. K.Boahen S. A.Frimpong M. M.Ujakpa et al. \u201cA Deep Multi\u2010Architectural Approach for Online Social Network Intrusion Detection System \u201d inProceedings of 2022 IEEE World Conference on Applied Intelligence and Computing AIC(2022) https:\/\/doi.org\/10.1109\/AIC55036.2022.9848865.","DOI":"10.1109\/AIC55036.2022.9848865"}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70334","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/ipr2.70334","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T12:13:02Z","timestamp":1773835982000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.70334"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1049\/ipr2.70334"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.70334","archive":["Portico"],"relation":{},"ISSN":["1751-9659","1751-9667"],"issn-type":[{"value":"1751-9659","type":"print"},{"value":"1751-9667","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-08-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70334"}}