An active search method for local individual features in off-line signature verification

We propose a new method of off‐line signature verification that extracts individual “peculiarities“ from parts of a signature and uses them for verification. In the registration process, reference signatures are compared with each other for correspondence estimation, and multiple areas exhibiting st...

Full description

Saved in:
Bibliographic Details
Published in:Systems and computers in Japan 2003-11, Vol.34 (12), p.64-76
Main Authors: Ando, Shingo, Nakajima, Masato
Format: Article
Language:English
Subjects:
correspondence estimation
genetic algorithm
local feature
off-line signature verification
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c2202-22b4d4b6a61797c287329b4339dab39d47646ce149067a9ae3ca250c627a4fc43
cites cdi_FETCH-LOGICAL-c2202-22b4d4b6a61797c287329b4339dab39d47646ce149067a9ae3ca250c627a4fc43
container_end_page 76
container_issue 12
container_start_page 64
container_title Systems and computers in Japan
container_volume 34
creator Ando, Shingo
Nakajima, Masato
description We propose a new method of off‐line signature verification that extracts individual “peculiarities“ from parts of a signature and uses them for verification. In the registration process, reference signatures are compared with each other for correspondence estimation, and multiple areas exhibiting strong individual peculiarities are extracted. In the verification process, correspondence estimation is first performed, then verification is performed with the extracted local features. We used multiscale regularization for correspondence estimation, and a genetic algorithm for extracting areas that exhibited strong individual peculiarities. As measures of the degree of individual peculiarities we used the magnitude of the deviation as determined from repeated signatures and the degree of complexity of the pen stroke. A verification experiment involving 20 subjects and their Japanese signatures (a total of 800 signatures) produced a best‐case average verification error rate of 2.63%. © 2003 Wiley Periodicals, Inc. Syst Comp Jpn, 34(12): 64–76, 2003; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10092
doi_str_mv 10.1002/scj.10092
format article
fullrecord <record><control><sourceid>wiley_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1002_scj_10092</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>SCJ10092</sourcerecordid><originalsourceid>FETCH-LOGICAL-c2202-22b4d4b6a61797c287329b4339dab39d47646ce149067a9ae3ca250c627a4fc43</originalsourceid><addsrcrecordid>eNp1kM1OAjEUhRujiYgufINuXVT6RztdEiIgIbpQA3HTdDqtFIcZ0w4ob-8A6s7c5N6Tk_PdxQHgmuBbgjHtJbvaC0VPQIf0KUYi44tT0MFZRhERQpyDi5RWGJN2VAcsBhU0tglbB5Mz0S7h2jXLuoC-jrCsrSlhqIqwDcWmld6ZZhNdaj1Ye4_KULVceKsONty6GHywpgl1dQnOvCmTu_q5XfAyunseTtDscXw_HMyQpRRTRGnOC54LI4hU0tJMMqpyzpgqTN4uLgUX1hGusJBGGcesoX1sBZWGe8tZF9wc_9pYpxSd1x8xrE3caYL1vhLdVqIPlbTZ3jH7GUq3-z-on4bTXwIdiZAa9_VHmPiuhWSyr-cPY52pxRyP8Kuesm9ubXI9</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>An active search method for local individual features in off-line signature verification</title><source>Wiley-Blackwell Journals</source><creator>Ando, Shingo ; Nakajima, Masato</creator><creatorcontrib>Ando, Shingo ; Nakajima, Masato</creatorcontrib><description>We propose a new method of off‐line signature verification that extracts individual “peculiarities“ from parts of a signature and uses them for verification. In the registration process, reference signatures are compared with each other for correspondence estimation, and multiple areas exhibiting strong individual peculiarities are extracted. In the verification process, correspondence estimation is first performed, then verification is performed with the extracted local features. We used multiscale regularization for correspondence estimation, and a genetic algorithm for extracting areas that exhibited strong individual peculiarities. As measures of the degree of individual peculiarities we used the magnitude of the deviation as determined from repeated signatures and the degree of complexity of the pen stroke. A verification experiment involving 20 subjects and their Japanese signatures (a total of 800 signatures) produced a best‐case average verification error rate of 2.63%. © 2003 Wiley Periodicals, Inc. Syst Comp Jpn, 34(12): 64–76, 2003; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10092</description><identifier>ISSN: 0882-1666</identifier><identifier>EISSN: 1520-684X</identifier><identifier>DOI: 10.1002/scj.10092</identifier><language>eng</language><publisher>Hoboken: Wiley Subscription Services, Inc., A Wiley Company</publisher><subject>correspondence estimation ; genetic algorithm ; local feature ; off-line signature verification</subject><ispartof>Systems and computers in Japan, 2003-11, Vol.34 (12), p.64-76</ispartof><rights>Copyright © 2003 Wiley Periodicals, Inc.</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c2202-22b4d4b6a61797c287329b4339dab39d47646ce149067a9ae3ca250c627a4fc43</citedby><cites>FETCH-LOGICAL-c2202-22b4d4b6a61797c287329b4339dab39d47646ce149067a9ae3ca250c627a4fc43</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1002%2Fscj.10092$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1002%2Fscj.10092$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>314,780,784,1416,27922,27923,45572,45573</link.rule.ids></links><search><creatorcontrib>Ando, Shingo</creatorcontrib><creatorcontrib>Nakajima, Masato</creatorcontrib><title>An active search method for local individual features in off-line signature verification</title><title>Systems and computers in Japan</title><addtitle>Syst. Comp. Jpn</addtitle><description>We propose a new method of off‐line signature verification that extracts individual “peculiarities“ from parts of a signature and uses them for verification. In the registration process, reference signatures are compared with each other for correspondence estimation, and multiple areas exhibiting strong individual peculiarities are extracted. In the verification process, correspondence estimation is first performed, then verification is performed with the extracted local features. We used multiscale regularization for correspondence estimation, and a genetic algorithm for extracting areas that exhibited strong individual peculiarities. As measures of the degree of individual peculiarities we used the magnitude of the deviation as determined from repeated signatures and the degree of complexity of the pen stroke. A verification experiment involving 20 subjects and their Japanese signatures (a total of 800 signatures) produced a best‐case average verification error rate of 2.63%. © 2003 Wiley Periodicals, Inc. Syst Comp Jpn, 34(12): 64–76, 2003; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10092</description><subject>correspondence estimation</subject><subject>genetic algorithm</subject><subject>local feature</subject><subject>off-line signature verification</subject><issn>0882-1666</issn><issn>1520-684X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2003</creationdate><recordtype>article</recordtype><recordid>eNp1kM1OAjEUhRujiYgufINuXVT6RztdEiIgIbpQA3HTdDqtFIcZ0w4ob-8A6s7c5N6Tk_PdxQHgmuBbgjHtJbvaC0VPQIf0KUYi44tT0MFZRhERQpyDi5RWGJN2VAcsBhU0tglbB5Mz0S7h2jXLuoC-jrCsrSlhqIqwDcWmld6ZZhNdaj1Ye4_KULVceKsONty6GHywpgl1dQnOvCmTu_q5XfAyunseTtDscXw_HMyQpRRTRGnOC54LI4hU0tJMMqpyzpgqTN4uLgUX1hGusJBGGcesoX1sBZWGe8tZF9wc_9pYpxSd1x8xrE3caYL1vhLdVqIPlbTZ3jH7GUq3-z-on4bTXwIdiZAa9_VHmPiuhWSyr-cPY52pxRyP8Kuesm9ubXI9</recordid><startdate>20031115</startdate><enddate>20031115</enddate><creator>Ando, Shingo</creator><creator>Nakajima, Masato</creator><general>Wiley Subscription Services, Inc., A Wiley Company</general><scope>BSCLL</scope><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20031115</creationdate><title>An active search method for local individual features in off-line signature verification</title><author>Ando, Shingo ; Nakajima, Masato</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c2202-22b4d4b6a61797c287329b4339dab39d47646ce149067a9ae3ca250c627a4fc43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2003</creationdate><topic>correspondence estimation</topic><topic>genetic algorithm</topic><topic>local feature</topic><topic>off-line signature verification</topic><toplevel>online_resources</toplevel><creatorcontrib>Ando, Shingo</creatorcontrib><creatorcontrib>Nakajima, Masato</creatorcontrib><collection>Istex</collection><collection>CrossRef</collection><jtitle>Systems and computers in Japan</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ando, Shingo</au><au>Nakajima, Masato</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An active search method for local individual features in off-line signature verification</atitle><jtitle>Systems and computers in Japan</jtitle><addtitle>Syst. Comp. Jpn</addtitle><date>2003-11-15</date><risdate>2003</risdate><volume>34</volume><issue>12</issue><spage>64</spage><epage>76</epage><pages>64-76</pages><issn>0882-1666</issn><eissn>1520-684X</eissn><abstract>We propose a new method of off‐line signature verification that extracts individual “peculiarities“ from parts of a signature and uses them for verification. In the registration process, reference signatures are compared with each other for correspondence estimation, and multiple areas exhibiting strong individual peculiarities are extracted. In the verification process, correspondence estimation is first performed, then verification is performed with the extracted local features. We used multiscale regularization for correspondence estimation, and a genetic algorithm for extracting areas that exhibited strong individual peculiarities. As measures of the degree of individual peculiarities we used the magnitude of the deviation as determined from repeated signatures and the degree of complexity of the pen stroke. A verification experiment involving 20 subjects and their Japanese signatures (a total of 800 signatures) produced a best‐case average verification error rate of 2.63%. © 2003 Wiley Periodicals, Inc. Syst Comp Jpn, 34(12): 64–76, 2003; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10092</abstract><cop>Hoboken</cop><pub>Wiley Subscription Services, Inc., A Wiley Company</pub><doi>10.1002/scj.10092</doi><tpages>13</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0882-1666
ispartof Systems and computers in Japan, 2003-11, Vol.34 (12), p.64-76
issn 0882-1666
1520-684X
language eng
recordid cdi_crossref_primary_10_1002_scj_10092
source Wiley-Blackwell Journals
subjects correspondence estimation
genetic algorithm
local feature
off-line signature verification
title An active search method for local individual features in off-line signature verification
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-13T11%3A40%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-wiley_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=An%20active%20search%20method%20for%20local%20individual%20features%20in%20off-line%20signature%20verification&rft.jtitle=Systems%20and%20computers%20in%20Japan&rft.au=Ando,%20Shingo&rft.date=2003-11-15&rft.volume=34&rft.issue=12&rft.spage=64&rft.epage=76&rft.pages=64-76&rft.issn=0882-1666&rft.eissn=1520-684X&rft_id=info:doi/10.1002/scj.10092&rft_dat=%3Cwiley_cross%3ESCJ10092%3C/wiley_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c2202-22b4d4b6a61797c287329b4339dab39d47646ce149067a9ae3ca250c627a4fc43%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true