Kinship Verification in Childhood Images Using Vision Transformer
Facial Kinship Verification involves determining whether two face images belong to relatives, a task that is particularly challenging due to subtle differences in facial features and large intra-class variations. In recent years, deep learning models have shown great promise in addressing this probl...
Uložené v:
| Vydané v: | Procedia computer science Ročník 258; s. 3105 - 3114 |
|---|---|
| Hlavní autori: | , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Elsevier B.V
2025
|
| Predmet: | |
| ISSN: | 1877-0509, 1877-0509 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Facial Kinship Verification involves determining whether two face images belong to relatives, a task that is particularly challenging due to subtle differences in facial features and large intra-class variations. In recent years, deep learning models have shown great promise in addressing this problem. In this work, we propose a Vision Transformer (ViT) model for facial Kinship Verification, leveraging the proven effectiveness of Transformer architectures in Natural Language Processing. The Vision Transformer is trained end-to-end on two benchmark datasets: the large-scale Families in the Wild (FIW) dataset, consisting of thousands of face images with corresponding kinship labels, and the smaller KinFaceW-II dataset. Our model employs multiple attention mechanisms to capture complex relationships between facial features and produce a final kinship prediction. Experimental results demonstrate that our approach outperforms state-of-the-art methods, achieving an average accuracy of 92% on the FIW dataset and an F1 score of 0.85. The Euclidean distance metric further enhances the classification of kin and non-kin pairs. These findings confirm the effectiveness of Vision Transformer models for facial Kinship Verification and underscore their potential for future research in this domain. |
|---|---|
| AbstractList | Facial Kinship Verification involves determining whether two face images belong to relatives, a task that is particularly challenging due to subtle differences in facial features and large intra-class variations. In recent years, deep learning models have shown great promise in addressing this problem. In this work, we propose a Vision Transformer (ViT) model for facial Kinship Verification, leveraging the proven effectiveness of Transformer architectures in Natural Language Processing. The Vision Transformer is trained end-to-end on two benchmark datasets: the large-scale Families in the Wild (FIW) dataset, consisting of thousands of face images with corresponding kinship labels, and the smaller KinFaceW-II dataset. Our model employs multiple attention mechanisms to capture complex relationships between facial features and produce a final kinship prediction. Experimental results demonstrate that our approach outperforms state-of-the-art methods, achieving an average accuracy of 92% on the FIW dataset and an F1 score of 0.85. The Euclidean distance metric further enhances the classification of kin and non-kin pairs. These findings confirm the effectiveness of Vision Transformer models for facial Kinship Verification and underscore their potential for future research in this domain. |
| Author | Meenpal, Toshanlal Majumdar, Saikat Oruganti, Madhu Tekchandani, Hitesh |
| Author_xml | – sequence: 1 givenname: Madhu surname: Oruganti fullname: Oruganti, Madhu email: madhu.oruganti@klh.edu.in organization: Asst. Prof., Department of AI & DS, Koneru Lakshmaiah Education Foundation, Aziz Nagar, Hyderabad, 500075, TG, India – sequence: 2 givenname: Toshanlal surname: Meenpal fullname: Meenpal, Toshanlal organization: Associate Prof., Department of ECE, National Institute of Technology, GE Road, Raipur, 492010, CG, India – sequence: 3 givenname: Saikat surname: Majumdar fullname: Majumdar, Saikat organization: Associate Prof., Department of ECE, National Institute of Technology, GE Road, Raipur, 492010, CG, India – sequence: 4 givenname: Hitesh surname: Tekchandani fullname: Tekchandani, Hitesh organization: Asst. Prof., Department of AI & DS, Koneru Lakshmaiah Education Foundation, Aziz Nagar, Hyderabad, 500075, TG, India |
| BookMark | eNqFkM1OAjEURhuDiYg8gZt5gRn7P52FC0JUiCRugG1T2w5cAi1pJya-vQO4MC70bu63uOcm37lFgxCDR-ie4IpgIh921TFFmyuKqagwr4RUV2hIVF2XWOBm8CPfoHHOO9wPU6oh9RBNXiHkLRyLtU_QgjUdxFBAKKZb2LttjK6YH8zG52KVIWyKNeTTwTKZkNuYDj7doevW7LMff-8RWj0_LaezcvH2Mp9OFqWlUqjScSNtI6R03Nec0dpTSbii75g1tRG0lUpSY4TpE_GYtZb2haywtTLMccxGiF3-2hRzTr7VxwQHkz41wfokQu_0WYQ-idCY615ETzW_KAvduWSXDOz_YR8vrO9rfYBPOlvwwXoHydtOuwh_8l8g3Xw8 |
| CitedBy_id | crossref_primary_10_1109_ACCESS_2025_3605630 |
| Cites_doi | 10.1109/ICME46284.2020.9102823 10.1007/s10044-020-00906-4 10.1016/j.compeleceng.2024.109375 10.1109/NCC52529.2021.9530084 10.1109/TPAMI.2013.134 10.1145/3134421.3134424 10.1109/TCYB.2022.3163707 10.1016/j.imavis.2023.104727 10.1016/j.jvcir.2021.103265 10.1109/FG52635.2021.9667009 10.1109/ICCCNT45670.2019.8944489 10.1109/TIP.2020.3034027 10.1109/CVPR.2015.7298621 10.1007/s11042-023-16694-y |
| ContentType | Journal Article |
| Copyright | 2025 The Author(s) |
| Copyright_xml | – notice: 2025 The Author(s) |
| DBID | 6I. AAFTH AAYXX CITATION |
| DOI | 10.1016/j.procs.2025.04.568 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1877-0509 |
| EndPage | 3114 |
| ExternalDocumentID | 10_1016_j_procs_2025_04_568 S1877050925016722 |
| GroupedDBID | --K 0R~ 1B1 457 5VS 6I. 71M 9DU AAEDT AAEDW AAFTH AAIKJ AALRI AAQFI AAXUO AAYWO ABMAC ABWVN ACGFS ACRPL ACVFH ADBBV ADCNI ADEZE ADNMO ADVLN AEUPX AEXQZ AFPUW AFTJW AGHFR AIGII AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ E3Z EBS EJD EP3 FDB FNPLU HZ~ IXB KQ8 M41 M~E O-L O9- OK1 P2P ROL SES SSZ ~HD AAYXX CITATION |
| ID | FETCH-LOGICAL-c2658-d4a6c9566d4e74327e261482b0397a52f6862aa5a2f61e03fc2202c5c78a3d403 |
| ISSN | 1877-0509 |
| IngestDate | Thu Nov 27 00:56:43 EST 2025 Tue Nov 18 20:35:42 EST 2025 Sat Nov 29 17:08:25 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Accuracy F1 Score Vision Transformers Childhood Images Facial Kinship Verification Binary Classification Problem |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c2658-d4a6c9566d4e74327e261482b0397a52f6862aa5a2f61e03fc2202c5c78a3d403 |
| OpenAccessLink | https://dx.doi.org/10.1016/j.procs.2025.04.568 |
| PageCount | 10 |
| ParticipantIDs | crossref_primary_10_1016_j_procs_2025_04_568 crossref_citationtrail_10_1016_j_procs_2025_04_568 elsevier_sciencedirect_doi_10_1016_j_procs_2025_04_568 |
| PublicationCentury | 2000 |
| PublicationDate | 2025 2025-00-00 |
| PublicationDateYYYYMMDD | 2025-01-01 |
| PublicationDate_xml | – year: 2025 text: 2025 |
| PublicationDecade | 2020 |
| PublicationTitle | Procedia computer science |
| PublicationYear | 2025 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Madhu Oruganti, Toshanlal Meenpal, and Saikat Majumder, ”Selective variance based kinship verification in parent’s childhood and their children,” in *2021 National Conference on Communications (NCC)*, IEEE, 2021, pp. 1–6. Yellow Class Childhood (YCCH) contest,” Facebook page Accessed: 2022-04-05. Jiaxuan Zhu, Ming Shao, Chao Xia, Hong Pan, and Siyu Xia, ”Adversarial attacks on kinship verification using transformer,” in *2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)*, 2021, pp. 1-8, doi Aarti Goyal and Toshanlal Meenpal, ”Eccentricity based kinship verification from facial images in the wild,” *Pattern Analysis and Applications*, vol. 24, pp. 119–144, 2021, Springer. Oruganti, Meenpal, Saikat (bib6857) 2024; 118 Moumita Mukherjee and Toshanlal Meenpal, ”Kinship verification using compound local binary pattern and local feature discriminant analysis,” in *2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)*, IEEE, 2019, pp. 1–7. Joseph P. Robinson, Ming Shao, Handong Zhao, Yue Wu, Timothy Gillis, and Yun Fu, ”Recognizing families in the wild (RFIW) data challenge workshop in conjunction with ACM MM 2017,” in *Proceedings of the 2017 Workshop on Recognizing Families in the Wild*, 2017, pp. 5–12. . Aarti Goyal and Toshanlal Meenpal, ”Patch-based dual-tree complex wavelet transform for kinship recognition,” *IEEE Transactions on Image Processing*, vol. 30, pp. 191–206, 2020, IEEE. Meenpal Oruganti and Saikat Majumder, ”Stationary wavelet transform features for kinship verification in childhood images,” *Multimedia Tools and Applications*, pp. 1–26, 2023, Springer. Sheng Huang, Jingkai Lin, Luwen Huangfu, Yun Xing, Junlin Hu, and Daniel Dajun Zeng, ”Adaptively weighted k-tuple metric network for kinship verification,” *IEEE Transactions on Cybernetics*, vol. 53, no. 10, pp. 6173–6186, 2022, IEEE. Wanhua Li, Yingqiang Zhang, Kangchen Lv, Jiwen Lu, Jianjiang Feng, and Jie Zhou, ”Graph-based kinship reasoning network,” in *2020 IEEE International Conference on Multimedia and Expo (ICME)*, IEEE, 2020, pp. 1–6. Jiwen Lu, Xiuzhuang Zhou, Yap-Pen Tan, Yuanyuan Shang, and Jie Zhou, ”Neighborhood repulsed metric learning for kinship verification,” *IEEE Transactions on Pattern Analysis and Machine Intelligence*, vol. 36, no. 2, pp. 331–345, 2013, IEEE. Yuting Zhang, Kihyuk Sohn, Ruben Villegas, Gang Pan, and Honglak Lee, ”Improving object detection with deep convolutional networks via bayesian optimization and structured prediction,” in *Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition*, 2015, pp. 249–258. Zhong, Yaoyao, and Weihong Deng. ”Face transformer for recognition.” arXiv preprint arXiv:2103.14803 (2021). Huishan Wu, Jiawei Chen, Xiao Liu, and Junlin Hu, ”Component-based metric learning for fully automatic kinship verification,” *Journal of Visual Communication and Image Representation*, vol. 79, p. 103265, 2021, Elsevier. Madhu Oruganti, Toshanlal Meenpal, and Saikat Majumder, ”Easy pair selection method for kinship verification using fixed age group images,” *Image and Vision Computing*, p. 104727, 2023, Elsevier. 10.1016/j.procs.2025.04.568_bib6868 10.1016/j.procs.2025.04.568_bib6867 10.1016/j.procs.2025.04.568_bib6859 10.1016/j.procs.2025.04.568_bib6858 10.1016/j.procs.2025.04.568_bib6869 10.1016/j.procs.2025.04.568_bib6864 10.1016/j.procs.2025.04.568_bib6863 10.1016/j.procs.2025.04.568_bib6866 10.1016/j.procs.2025.04.568_bib6865 10.1016/j.procs.2025.04.568_bib6860 10.1016/j.procs.2025.04.568_bib6871 10.1016/j.procs.2025.04.568_bib6870 10.1016/j.procs.2025.04.568_bib6862 10.1016/j.procs.2025.04.568_bib6861 10.1016/j.procs.2025.04.568_bib6872 Oruganti (10.1016/j.procs.2025.04.568_bib6857) 2024; 118 |
| References_xml | – reference: Madhu Oruganti, Toshanlal Meenpal, and Saikat Majumder, ”Easy pair selection method for kinship verification using fixed age group images,” *Image and Vision Computing*, p. 104727, 2023, Elsevier. – reference: , Accessed: 2022-04-05. – reference: Madhu Oruganti, Toshanlal Meenpal, and Saikat Majumder, ”Selective variance based kinship verification in parent’s childhood and their children,” in *2021 National Conference on Communications (NCC)*, IEEE, 2021, pp. 1–6. – reference: Yuting Zhang, Kihyuk Sohn, Ruben Villegas, Gang Pan, and Honglak Lee, ”Improving object detection with deep convolutional networks via bayesian optimization and structured prediction,” in *Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition*, 2015, pp. 249–258. – reference: Wanhua Li, Yingqiang Zhang, Kangchen Lv, Jiwen Lu, Jianjiang Feng, and Jie Zhou, ”Graph-based kinship reasoning network,” in *2020 IEEE International Conference on Multimedia and Expo (ICME)*, IEEE, 2020, pp. 1–6. – reference: Aarti Goyal and Toshanlal Meenpal, ”Eccentricity based kinship verification from facial images in the wild,” *Pattern Analysis and Applications*, vol. 24, pp. 119–144, 2021, Springer. – reference: Huishan Wu, Jiawei Chen, Xiao Liu, and Junlin Hu, ”Component-based metric learning for fully automatic kinship verification,” *Journal of Visual Communication and Image Representation*, vol. 79, p. 103265, 2021, Elsevier. – reference: Joseph P. Robinson, Ming Shao, Handong Zhao, Yue Wu, Timothy Gillis, and Yun Fu, ”Recognizing families in the wild (RFIW) data challenge workshop in conjunction with ACM MM 2017,” in *Proceedings of the 2017 Workshop on Recognizing Families in the Wild*, 2017, pp. 5–12. – reference: Sheng Huang, Jingkai Lin, Luwen Huangfu, Yun Xing, Junlin Hu, and Daniel Dajun Zeng, ”Adaptively weighted k-tuple metric network for kinship verification,” *IEEE Transactions on Cybernetics*, vol. 53, no. 10, pp. 6173–6186, 2022, IEEE. – reference: . – reference: Meenpal Oruganti and Saikat Majumder, ”Stationary wavelet transform features for kinship verification in childhood images,” *Multimedia Tools and Applications*, pp. 1–26, 2023, Springer. – reference: ”Yellow Class Childhood (YCCH) contest,” Facebook page, – volume: 118 start-page: 109375 year: 2024 ident: bib6857 article-title: ”Kinship verification in childhood images using curvelet transformed features." publication-title: Computers and Electrical Engineering – reference: Zhong, Yaoyao, and Weihong Deng. ”Face transformer for recognition.” arXiv preprint arXiv:2103.14803 (2021). – reference: Moumita Mukherjee and Toshanlal Meenpal, ”Kinship verification using compound local binary pattern and local feature discriminant analysis,” in *2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)*, IEEE, 2019, pp. 1–7. – reference: Jiwen Lu, Xiuzhuang Zhou, Yap-Pen Tan, Yuanyuan Shang, and Jie Zhou, ”Neighborhood repulsed metric learning for kinship verification,” *IEEE Transactions on Pattern Analysis and Machine Intelligence*, vol. 36, no. 2, pp. 331–345, 2013, IEEE. – reference: Aarti Goyal and Toshanlal Meenpal, ”Patch-based dual-tree complex wavelet transform for kinship recognition,” *IEEE Transactions on Image Processing*, vol. 30, pp. 191–206, 2020, IEEE. – reference: Jiaxuan Zhu, Ming Shao, Chao Xia, Hong Pan, and Siyu Xia, ”Adversarial attacks on kinship verification using transformer,” in *2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)*, 2021, pp. 1-8, doi: – ident: 10.1016/j.procs.2025.04.568_bib6871 – ident: 10.1016/j.procs.2025.04.568_bib6867 doi: 10.1109/ICME46284.2020.9102823 – ident: 10.1016/j.procs.2025.04.568_bib6870 doi: 10.1007/s10044-020-00906-4 – volume: 118 start-page: 109375 year: 2024 ident: 10.1016/j.procs.2025.04.568_bib6857 article-title: ”Kinship verification in childhood images using curvelet transformed features." publication-title: Computers and Electrical Engineering doi: 10.1016/j.compeleceng.2024.109375 – ident: 10.1016/j.procs.2025.04.568_bib6872 – ident: 10.1016/j.procs.2025.04.568_bib6863 doi: 10.1109/NCC52529.2021.9530084 – ident: 10.1016/j.procs.2025.04.568_bib6859 doi: 10.1109/TPAMI.2013.134 – ident: 10.1016/j.procs.2025.04.568_bib6861 doi: 10.1145/3134421.3134424 – ident: 10.1016/j.procs.2025.04.568_bib6865 doi: 10.1109/TCYB.2022.3163707 – ident: 10.1016/j.procs.2025.04.568_bib6864 doi: 10.1016/j.imavis.2023.104727 – ident: 10.1016/j.procs.2025.04.568_bib6862 doi: 10.1016/j.jvcir.2021.103265 – ident: 10.1016/j.procs.2025.04.568_bib6866 doi: 10.1109/FG52635.2021.9667009 – ident: 10.1016/j.procs.2025.04.568_bib6858 doi: 10.1109/ICCCNT45670.2019.8944489 – ident: 10.1016/j.procs.2025.04.568_bib6868 doi: 10.1109/TIP.2020.3034027 – ident: 10.1016/j.procs.2025.04.568_bib6860 doi: 10.1109/CVPR.2015.7298621 – ident: 10.1016/j.procs.2025.04.568_bib6869 doi: 10.1007/s11042-023-16694-y |
| SSID | ssj0000388917 |
| Score | 2.3492646 |
| Snippet | Facial Kinship Verification involves determining whether two face images belong to relatives, a task that is particularly challenging due to subtle differences... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 3105 |
| SubjectTerms | Accuracy Binary Classification Problem Childhood Images F1 Score Facial Kinship Verification Vision Transformers |
| Title | Kinship Verification in Childhood Images Using Vision Transformer |
| URI | https://dx.doi.org/10.1016/j.procs.2025.04.568 |
| Volume | 258 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 1877-0509 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000388917 issn: 1877-0509 databaseCode: M~E dateStart: 20100101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3PT9swFLYK24HL2C80fmzygVsXKXWcOjkiBGLahiZRKm6RaztrSwlVSxEn_gH-aZ79HJMBqsaBS5RajdPkffV7fnrf9wjZzWWadVXCopIzDhsUqaMB02UkNPj3zJI_XSq7_0scH2dnZ_mfVuuu5sJcT0RVZTc3-fRVTQ1jYGxLnX2BucOkMADnYHQ4gtnh-F-G_znCCqw-3Kz0GTnH7Qsixj8upFV2wGqBviOXo8i5DWB9ta6PVx2PACDkSs9t94e2d5khOTtb_AXjjJD3o4eLYEHYIE9dN4F273I-lNVEPpQgyvHiQmNp94njMIUEgjm3VGSNnabaRxAQz4fNzATyl_0ymgkRWWUZ9DLPjPm1l6Fuu189IdRMG5446SC_9MkqjwmHsfUxykqus9TK1abYn-dfTe1Hvi5UINbFbePCTVLYSYqYFzDJCnnDRJrb-sDftw8JOyubk7sOzuFJahUrVy_45Mc8H-k0opfee_LObzvoHsLlA2mZ6iNZr1t6UL_CfyJ7Hj20iR46qmhAD0X0UIceiuihDfR8JqeHB739o8h32YgUg_Az0lx2FeySu5obCCeZMMyJww5iCFVlykrLIZIylXDWMXFSKgYPqVIlMploHicbZLW6rMwXQpOOVFyKjiyZ5LEBXzAwXGU5iwe8VHG5SVj9RgrlJehtJ5RJscQcm-R7uGiKCizLv96tX3Xh_xEYHBaAnmUXbr3sPttkzX7CbNwOWb2aLcxX8lZdX43ms28OOvcym5RQ |
| linkProvider | ISSN International Centre |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Kinship+Verification+in+Childhood+Images+Using+Vision+Transformer&rft.jtitle=Procedia+computer+science&rft.au=Oruganti%2C+Madhu&rft.au=Meenpal%2C+Toshanlal&rft.au=Majumdar%2C+Saikat&rft.au=Tekchandani%2C+Hitesh&rft.date=2025&rft.issn=1877-0509&rft.eissn=1877-0509&rft.volume=258&rft.spage=3105&rft.epage=3114&rft_id=info:doi/10.1016%2Fj.procs.2025.04.568&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_procs_2025_04_568 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1877-0509&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1877-0509&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1877-0509&client=summon |