Handwritten signature verification system using hybrid transfer learning approach
The shortage of annotated images for handwritten signature verification continues to be a significant problem. However, making inferences from such a small amount of data is difficult. This article presents a novel approach for offline signature verification based on modified VGG19 transfer learning...
Gespeichert in:
| Veröffentlicht in: | Evolving systems 2024-12, Vol.15 (6), p.2313-2322 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2322 |
|---|---|
| container_issue | 6 |
| container_start_page | 2313 |
| container_title | Evolving systems |
| container_volume | 15 |
| creator | Upadhyay, Rashmi Rathi Singh, Koushlendra Kumar |
| description | The shortage of annotated images for handwritten signature verification continues to be a significant problem. However, making inferences from such a small amount of data is difficult. This article presents a novel approach for offline signature verification based on modified VGG19 transfer learning, which is a deep learning strategy to develop an unbiased model with high accuracy. The proposed model is validated with the data set BHSig260, which is in the Bengali language. The study used the pretrained model VGG-19 to extract features from each layer, followed by typical classification machine learning approaches. The suggested model has been validated using the various parameters, and it has a 97.8% accuracy with modified VGG19 and Random Forest. A comparison between the suggested method and the various current methods is also discussed in the study. |
| doi_str_mv | 10.1007/s12530-024-09617-1 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_3118957456</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3118957456</sourcerecordid><originalsourceid>FETCH-LOGICAL-c200t-fe876106ca59bca805715572457264de2d6806dcf75b6db3488f1c02a39303cf3</originalsourceid><addsrcrecordid>eNp9kE9LAzEQxYMoWLRfwNOC59XJ__QoRa1QEEHPIZtN2pR2tyZZpd_e1BW9eRhmmHnvDfwQusJwgwHkbcKEU6iBsBpmAssan6AJVkLVgilx-jtLdY6mKW0AgGAGwOQEvSxM137GkLPrqhRWnclDdNWHi8EHa3Loy_qQsttVQwrdqlofmhjaKkfTJe9itXUmdseD2e9jb-z6Ep15s01u-tMv0NvD_et8US-fH5_md8vaEoBce6ekwCCs4bPGGgVcYs4lYaUEax1phQLRWi95I9qGMqU8tkAMnVGg1tMLdD3mlrfvg0tZb_ohduWlphirGZeMi6Iio8rGPqXovN7HsDPxoDHoIz090tOFnv6mp3Ex0dGUirhbufgX_Y_rC73scrY</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3118957456</pqid></control><display><type>article</type><title>Handwritten signature verification system using hybrid transfer learning approach</title><source>SpringerLink Journals</source><creator>Upadhyay, Rashmi Rathi ; Singh, Koushlendra Kumar</creator><creatorcontrib>Upadhyay, Rashmi Rathi ; Singh, Koushlendra Kumar</creatorcontrib><description>The shortage of annotated images for handwritten signature verification continues to be a significant problem. However, making inferences from such a small amount of data is difficult. This article presents a novel approach for offline signature verification based on modified VGG19 transfer learning, which is a deep learning strategy to develop an unbiased model with high accuracy. The proposed model is validated with the data set BHSig260, which is in the Bengali language. The study used the pretrained model VGG-19 to extract features from each layer, followed by typical classification machine learning approaches. The suggested model has been validated using the various parameters, and it has a 97.8% accuracy with modified VGG19 and Random Forest. A comparison between the suggested method and the various current methods is also discussed in the study.</description><identifier>ISSN: 1868-6478</identifier><identifier>EISSN: 1868-6486</identifier><identifier>DOI: 10.1007/s12530-024-09617-1</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Artificial Intelligence ; Biometrics ; Complex Systems ; Complexity ; Deep learning ; Engineering ; Forgery ; Handwriting ; Handwritten signature verification ; Machine learning ; Neural networks ; Original Paper ; Parameter modification ; Random variables ; Signatures</subject><ispartof>Evolving systems, 2024-12, Vol.15 (6), p.2313-2322</ispartof><rights>The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c200t-fe876106ca59bca805715572457264de2d6806dcf75b6db3488f1c02a39303cf3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s12530-024-09617-1$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s12530-024-09617-1$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,776,780,27901,27902,41464,42533,51294</link.rule.ids></links><search><creatorcontrib>Upadhyay, Rashmi Rathi</creatorcontrib><creatorcontrib>Singh, Koushlendra Kumar</creatorcontrib><title>Handwritten signature verification system using hybrid transfer learning approach</title><title>Evolving systems</title><addtitle>Evolving Systems</addtitle><description>The shortage of annotated images for handwritten signature verification continues to be a significant problem. However, making inferences from such a small amount of data is difficult. This article presents a novel approach for offline signature verification based on modified VGG19 transfer learning, which is a deep learning strategy to develop an unbiased model with high accuracy. The proposed model is validated with the data set BHSig260, which is in the Bengali language. The study used the pretrained model VGG-19 to extract features from each layer, followed by typical classification machine learning approaches. The suggested model has been validated using the various parameters, and it has a 97.8% accuracy with modified VGG19 and Random Forest. A comparison between the suggested method and the various current methods is also discussed in the study.</description><subject>Artificial Intelligence</subject><subject>Biometrics</subject><subject>Complex Systems</subject><subject>Complexity</subject><subject>Deep learning</subject><subject>Engineering</subject><subject>Forgery</subject><subject>Handwriting</subject><subject>Handwritten signature verification</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Original Paper</subject><subject>Parameter modification</subject><subject>Random variables</subject><subject>Signatures</subject><issn>1868-6478</issn><issn>1868-6486</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kE9LAzEQxYMoWLRfwNOC59XJ__QoRa1QEEHPIZtN2pR2tyZZpd_e1BW9eRhmmHnvDfwQusJwgwHkbcKEU6iBsBpmAssan6AJVkLVgilx-jtLdY6mKW0AgGAGwOQEvSxM137GkLPrqhRWnclDdNWHi8EHa3Loy_qQsttVQwrdqlofmhjaKkfTJe9itXUmdseD2e9jb-z6Ep15s01u-tMv0NvD_et8US-fH5_md8vaEoBce6ekwCCs4bPGGgVcYs4lYaUEax1phQLRWi95I9qGMqU8tkAMnVGg1tMLdD3mlrfvg0tZb_ohduWlphirGZeMi6Iio8rGPqXovN7HsDPxoDHoIz090tOFnv6mp3Ex0dGUirhbufgX_Y_rC73scrY</recordid><startdate>20241201</startdate><enddate>20241201</enddate><creator>Upadhyay, Rashmi Rathi</creator><creator>Singh, Koushlendra Kumar</creator><general>Springer Berlin Heidelberg</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>JQ2</scope></search><sort><creationdate>20241201</creationdate><title>Handwritten signature verification system using hybrid transfer learning approach</title><author>Upadhyay, Rashmi Rathi ; Singh, Koushlendra Kumar</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c200t-fe876106ca59bca805715572457264de2d6806dcf75b6db3488f1c02a39303cf3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Artificial Intelligence</topic><topic>Biometrics</topic><topic>Complex Systems</topic><topic>Complexity</topic><topic>Deep learning</topic><topic>Engineering</topic><topic>Forgery</topic><topic>Handwriting</topic><topic>Handwritten signature verification</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Original Paper</topic><topic>Parameter modification</topic><topic>Random variables</topic><topic>Signatures</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Upadhyay, Rashmi Rathi</creatorcontrib><creatorcontrib>Singh, Koushlendra Kumar</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Computer Science Collection</collection><jtitle>Evolving systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Upadhyay, Rashmi Rathi</au><au>Singh, Koushlendra Kumar</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Handwritten signature verification system using hybrid transfer learning approach</atitle><jtitle>Evolving systems</jtitle><stitle>Evolving Systems</stitle><date>2024-12-01</date><risdate>2024</risdate><volume>15</volume><issue>6</issue><spage>2313</spage><epage>2322</epage><pages>2313-2322</pages><issn>1868-6478</issn><eissn>1868-6486</eissn><abstract>The shortage of annotated images for handwritten signature verification continues to be a significant problem. However, making inferences from such a small amount of data is difficult. This article presents a novel approach for offline signature verification based on modified VGG19 transfer learning, which is a deep learning strategy to develop an unbiased model with high accuracy. The proposed model is validated with the data set BHSig260, which is in the Bengali language. The study used the pretrained model VGG-19 to extract features from each layer, followed by typical classification machine learning approaches. The suggested model has been validated using the various parameters, and it has a 97.8% accuracy with modified VGG19 and Random Forest. A comparison between the suggested method and the various current methods is also discussed in the study.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/s12530-024-09617-1</doi><tpages>10</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1868-6478 |
| ispartof | Evolving systems, 2024-12, Vol.15 (6), p.2313-2322 |
| issn | 1868-6478 1868-6486 |
| language | eng |
| recordid | cdi_proquest_journals_3118957456 |
| source | SpringerLink Journals |
| subjects | Artificial Intelligence Biometrics Complex Systems Complexity Deep learning Engineering Forgery Handwriting Handwritten signature verification Machine learning Neural networks Original Paper Parameter modification Random variables Signatures |
| title | Handwritten signature verification system using hybrid transfer learning approach |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T01%3A50%3A42IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Handwritten%20signature%20verification%20system%20using%20hybrid%20transfer%20learning%20approach&rft.jtitle=Evolving%20systems&rft.au=Upadhyay,%20Rashmi%20Rathi&rft.date=2024-12-01&rft.volume=15&rft.issue=6&rft.spage=2313&rft.epage=2322&rft.pages=2313-2322&rft.issn=1868-6478&rft.eissn=1868-6486&rft_id=info:doi/10.1007/s12530-024-09617-1&rft_dat=%3Cproquest_cross%3E3118957456%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3118957456&rft_id=info:pmid/&rfr_iscdi=true |