Two heads are better than one: Dual systems obtain better performance in facial comparison
Forensic facial image comparison based on recognition algorithms has been widely applied in forensic science. Previous researches have been concentrating on the cases of using single system during comparison, while how to use multiple systems has not yet been studied. In this paper, a dual-systems m...
Gespeichert in:
| Veröffentlicht in: | Forensic science international 2023-12, Vol.353, p.111879-111879, Article 111879 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 111879 |
|---|---|
| container_issue | |
| container_start_page | 111879 |
| container_title | Forensic science international |
| container_volume | 353 |
| creator | Li, Zhihui Xie, Lanchi Song, Huaqing |
| description | Forensic facial image comparison based on recognition algorithms has been widely applied in forensic science. Previous researches have been concentrating on the cases of using single system during comparison, while how to use multiple systems has not yet been studied. In this paper, a dual-systems model (including SeetaFace and FaceNet) for facial comparison was constructed, and Bayesian networks were utilized as the basic frame. In order to prove its superiority, a large-scale experiment (on the dataset CelebA) has been carried on to evaluate the score-based likelihood ratio. We used three likelihood ratio evaluation tools (Empirical Cross-Entropy, Cost Likelihood Ratio, Limit Tippett Plots) to assess the performance of the model. The Wasserstein distance was also used to evaluate the detailed likelihood ratio performance. The experimental results show that the likelihood ratio performance of our dual-systems model is better than single system. Besides, our method of model building and evaluation can also be used in the condition of triple or more systems. |
| doi_str_mv | 10.1016/j.forsciint.2023.111879 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2889243055</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2896083664</sourcerecordid><originalsourceid>FETCH-LOGICAL-c318t-386d5665698d9793f5b22d568a9d94f2ee9c7005ffa05985e92688ad398d2aaf3</originalsourceid><addsrcrecordid>eNpdkMtKxDAUhoMoOF6ewYAbNx1zmaaJOxmvMOBm3LgJmfSEaWmbmqTIvL0ZRl24OvDzcc5_PoSuKJlTQsVtO3c-RNs0Q5ozwvicUiordYRmebBCMMmP0YzwShWk4vIUncXYEkLKkokZ-lh_ebwFU0dsAuANpAQBp60ZsB_gDj9MpsNxFxP0EftNMs3wC40Q8uXeDBZwTp2xTWat70cTmuiHC3TiTBfh8meeo_enx_XypVi9Pb8u71eF5VSmgktRl0KUQslaVYq7csNYTqRRtVo4BqBsles6Z0ipZAmKCSlNzTPPjHH8HN0c9o7Bf04Qk-6baKHrzAB-ippJqdiC54czev0Pbf0UhtwuU0oQyYVYZKo6UDb4GAM4PYamN2GnKdF757rVf8713rk-OOffPMR4CQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2896083664</pqid></control><display><type>article</type><title>Two heads are better than one: Dual systems obtain better performance in facial comparison</title><source>Access via ScienceDirect (Elsevier)</source><source>ProQuest Central UK/Ireland</source><creator>Li, Zhihui ; Xie, Lanchi ; Song, Huaqing</creator><creatorcontrib>Li, Zhihui ; Xie, Lanchi ; Song, Huaqing</creatorcontrib><description>Forensic facial image comparison based on recognition algorithms has been widely applied in forensic science. Previous researches have been concentrating on the cases of using single system during comparison, while how to use multiple systems has not yet been studied. In this paper, a dual-systems model (including SeetaFace and FaceNet) for facial comparison was constructed, and Bayesian networks were utilized as the basic frame. In order to prove its superiority, a large-scale experiment (on the dataset CelebA) has been carried on to evaluate the score-based likelihood ratio. We used three likelihood ratio evaluation tools (Empirical Cross-Entropy, Cost Likelihood Ratio, Limit Tippett Plots) to assess the performance of the model. The Wasserstein distance was also used to evaluate the detailed likelihood ratio performance. The experimental results show that the likelihood ratio performance of our dual-systems model is better than single system. Besides, our method of model building and evaluation can also be used in the condition of triple or more systems.</description><identifier>ISSN: 0379-0738</identifier><identifier>EISSN: 1872-6283</identifier><identifier>DOI: 10.1016/j.forsciint.2023.111879</identifier><language>eng</language><publisher>Amsterdam: Elsevier Limited</publisher><subject>Accuracy ; Algorithms ; Bayesian analysis ; Biometrics ; Entropy (Information theory) ; Face ; Forensic science ; Forensic sciences ; Hypotheses ; Likelihood ratio ; Methods ; Neural networks ; Performance assessment ; Performance evaluation ; Probability</subject><ispartof>Forensic science international, 2023-12, Vol.353, p.111879-111879, Article 111879</ispartof><rights>2023. Elsevier B.V.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c318t-386d5665698d9793f5b22d568a9d94f2ee9c7005ffa05985e92688ad398d2aaf3</citedby><cites>FETCH-LOGICAL-c318t-386d5665698d9793f5b22d568a9d94f2ee9c7005ffa05985e92688ad398d2aaf3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2896083664?pq-origsite=primo$$EHTML$$P50$$Gproquest$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,64385,64387,64389,72469</link.rule.ids></links><search><creatorcontrib>Li, Zhihui</creatorcontrib><creatorcontrib>Xie, Lanchi</creatorcontrib><creatorcontrib>Song, Huaqing</creatorcontrib><title>Two heads are better than one: Dual systems obtain better performance in facial comparison</title><title>Forensic science international</title><description>Forensic facial image comparison based on recognition algorithms has been widely applied in forensic science. Previous researches have been concentrating on the cases of using single system during comparison, while how to use multiple systems has not yet been studied. In this paper, a dual-systems model (including SeetaFace and FaceNet) for facial comparison was constructed, and Bayesian networks were utilized as the basic frame. In order to prove its superiority, a large-scale experiment (on the dataset CelebA) has been carried on to evaluate the score-based likelihood ratio. We used three likelihood ratio evaluation tools (Empirical Cross-Entropy, Cost Likelihood Ratio, Limit Tippett Plots) to assess the performance of the model. The Wasserstein distance was also used to evaluate the detailed likelihood ratio performance. The experimental results show that the likelihood ratio performance of our dual-systems model is better than single system. Besides, our method of model building and evaluation can also be used in the condition of triple or more systems.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>Bayesian analysis</subject><subject>Biometrics</subject><subject>Entropy (Information theory)</subject><subject>Face</subject><subject>Forensic science</subject><subject>Forensic sciences</subject><subject>Hypotheses</subject><subject>Likelihood ratio</subject><subject>Methods</subject><subject>Neural networks</subject><subject>Performance assessment</subject><subject>Performance evaluation</subject><subject>Probability</subject><issn>0379-0738</issn><issn>1872-6283</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>8G5</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><sourceid>GUQSH</sourceid><sourceid>M2O</sourceid><recordid>eNpdkMtKxDAUhoMoOF6ewYAbNx1zmaaJOxmvMOBm3LgJmfSEaWmbmqTIvL0ZRl24OvDzcc5_PoSuKJlTQsVtO3c-RNs0Q5ozwvicUiordYRmebBCMMmP0YzwShWk4vIUncXYEkLKkokZ-lh_ebwFU0dsAuANpAQBp60ZsB_gDj9MpsNxFxP0EftNMs3wC40Q8uXeDBZwTp2xTWat70cTmuiHC3TiTBfh8meeo_enx_XypVi9Pb8u71eF5VSmgktRl0KUQslaVYq7csNYTqRRtVo4BqBsles6Z0ipZAmKCSlNzTPPjHH8HN0c9o7Bf04Qk-6baKHrzAB-ippJqdiC54czev0Pbf0UhtwuU0oQyYVYZKo6UDb4GAM4PYamN2GnKdF757rVf8713rk-OOffPMR4CQ</recordid><startdate>20231201</startdate><enddate>20231201</enddate><creator>Li, Zhihui</creator><creator>Xie, Lanchi</creator><creator>Song, Huaqing</creator><general>Elsevier Limited</general><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7QP</scope><scope>7RV</scope><scope>7U7</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8FE</scope><scope>8FH</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>8G5</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BHPHI</scope><scope>C1K</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>GNUQQ</scope><scope>GUQSH</scope><scope>HCIFZ</scope><scope>K9.</scope><scope>KB0</scope><scope>LK8</scope><scope>M0S</scope><scope>M1P</scope><scope>M2O</scope><scope>M7P</scope><scope>MBDVC</scope><scope>NAPCQ</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>Q9U</scope><scope>7X8</scope></search><sort><creationdate>20231201</creationdate><title>Two heads are better than one: Dual systems obtain better performance in facial comparison</title><author>Li, Zhihui ; Xie, Lanchi ; Song, Huaqing</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c318t-386d5665698d9793f5b22d568a9d94f2ee9c7005ffa05985e92688ad398d2aaf3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>Bayesian analysis</topic><topic>Biometrics</topic><topic>Entropy (Information theory)</topic><topic>Face</topic><topic>Forensic science</topic><topic>Forensic sciences</topic><topic>Hypotheses</topic><topic>Likelihood ratio</topic><topic>Methods</topic><topic>Neural networks</topic><topic>Performance assessment</topic><topic>Performance evaluation</topic><topic>Probability</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Li, Zhihui</creatorcontrib><creatorcontrib>Xie, Lanchi</creatorcontrib><creatorcontrib>Song, Huaqing</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Calcium & Calcified Tissue Abstracts</collection><collection>Nursing & Allied Health Database</collection><collection>Toxicology Abstracts</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>Research Library (Alumni Edition)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>Biological Science Collection</collection><collection>ProQuest Central</collection><collection>Natural Science Collection</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Central Student</collection><collection>Research Library Prep</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Nursing & Allied Health Database (Alumni Edition)</collection><collection>ProQuest Biological Science Collection</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>Research Library</collection><collection>Biological Science Database</collection><collection>Research Library (Corporate)</collection><collection>Nursing & Allied Health Premium</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central Basic</collection><collection>MEDLINE - Academic</collection><jtitle>Forensic science international</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Li, Zhihui</au><au>Xie, Lanchi</au><au>Song, Huaqing</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Two heads are better than one: Dual systems obtain better performance in facial comparison</atitle><jtitle>Forensic science international</jtitle><date>2023-12-01</date><risdate>2023</risdate><volume>353</volume><spage>111879</spage><epage>111879</epage><pages>111879-111879</pages><artnum>111879</artnum><issn>0379-0738</issn><eissn>1872-6283</eissn><abstract>Forensic facial image comparison based on recognition algorithms has been widely applied in forensic science. Previous researches have been concentrating on the cases of using single system during comparison, while how to use multiple systems has not yet been studied. In this paper, a dual-systems model (including SeetaFace and FaceNet) for facial comparison was constructed, and Bayesian networks were utilized as the basic frame. In order to prove its superiority, a large-scale experiment (on the dataset CelebA) has been carried on to evaluate the score-based likelihood ratio. We used three likelihood ratio evaluation tools (Empirical Cross-Entropy, Cost Likelihood Ratio, Limit Tippett Plots) to assess the performance of the model. The Wasserstein distance was also used to evaluate the detailed likelihood ratio performance. The experimental results show that the likelihood ratio performance of our dual-systems model is better than single system. Besides, our method of model building and evaluation can also be used in the condition of triple or more systems.</abstract><cop>Amsterdam</cop><pub>Elsevier Limited</pub><doi>10.1016/j.forsciint.2023.111879</doi><tpages>1</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0379-0738 |
| ispartof | Forensic science international, 2023-12, Vol.353, p.111879-111879, Article 111879 |
| issn | 0379-0738 1872-6283 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2889243055 |
| source | Access via ScienceDirect (Elsevier); ProQuest Central UK/Ireland |
| subjects | Accuracy Algorithms Bayesian analysis Biometrics Entropy (Information theory) Face Forensic science Forensic sciences Hypotheses Likelihood ratio Methods Neural networks Performance assessment Performance evaluation Probability |
| title | Two heads are better than one: Dual systems obtain better performance in facial comparison |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-21T07%3A50%3A01IST&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=Two%20heads%20are%20better%20than%20one:%20Dual%20systems%20obtain%20better%20performance%20in%20facial%20comparison&rft.jtitle=Forensic%20science%20international&rft.au=Li,%20Zhihui&rft.date=2023-12-01&rft.volume=353&rft.spage=111879&rft.epage=111879&rft.pages=111879-111879&rft.artnum=111879&rft.issn=0379-0738&rft.eissn=1872-6283&rft_id=info:doi/10.1016/j.forsciint.2023.111879&rft_dat=%3Cproquest_cross%3E2896083664%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=2896083664&rft_id=info:pmid/&rfr_iscdi=true |