Multi-Descriptor Fusion with Deep Residual Learning for Kinshipship Identification from Facial Images
DOI:
https://doi.org/10.62411/jcta.16066Keywords:
Deep Learning, Facial Kinship Recognition, Feature Fusion, Hybrid Framework, KinFaceW-I, Machine Learning, ResNet-50, Support Vector MachineAbstract
Kinship identification from facial images aims to determine biological relationships between individuals based on shared facial characteristics. However, subtle kinship-related facial cues are often obscured by variations in illumination, pose, age, and facial expressions, making reliable kinship classification challenging. To address this problem, this study proposes a hybrid framework that integrates handcrafted texture descriptors with deep features for multiclass kinship identification. A preprocessing pipeline consisting of image resizing to 224 × 224 pixels, noise reduction, intensity normalization, and facial region extraction is first applied to improve image consistency and feature quality. Three complementary local texture descriptors, namely Local Binary Pattern (LBP), Local Ternary Pattern (LTP), and Local Directional Pattern (LDP), are then employed to capture fine-grained facial texture and directional information. These handcrafted representations are fused with 2048-dimensional deep features extracted from a ResNet-50 model. The resulting 4562-dimensional pair representation is classified using a Support Vector Machine (SVM) under a four-class setting comprising father–son, father–daughter, mother–son, and mother–daughter relationships. Experiments on the KinFaceW-I dataset demonstrate that the proposed hybrid framework achieves a mean accuracy of 82.97%, with mean precision, recall, and F1-score of 82.99%, 83.00%, and 82.98%, respectively. The results further show consistent performance across all four relationship categories and competitive performance against existing methods, demonstrating the effectiveness of combining complementary local texture descriptors with deep semantic representations.References
R. Li et al., “Easykin: a flexible and user-friendly online tool for forensic kinship testing and missing person identification,” Int. J. Legal Med., vol. 137, no. 6, pp. 1671–1681, Nov. 2023, doi: 10.1007/s00414-023-03083-1.
G. Cosenza, L. Castellino, S. Morelli, E. Alladio, and E. Pilli, “Kinship analysis and machine learning algorithms in forensic contexts: A new NGS panel,” Expert Syst. Appl., vol. 266, p. 126161, Mar. 2025, doi: 10.1016/j.eswa.2024.126161.
E. Haimes, “Social and Ethical Issues in the Use of Familial Searching in Forensic Investigations: Insights from Family and Kinship Studies,” J. Law, Med. Ethics, vol. 34, no. 2, pp. 263–276, Jan. 2006, doi: 10.1111/j.1748-720X.2006.00032.x.
L. Han, “New Technologies in Combating Child Trafficking in China: Opportunities and Challenges for Children’s Rights,” Peace Hum. Rights Gov., vol. 3, no. 3, pp. 389–414, 2019, doi: 10.14658/PUPJ-PHRG-2019-3-5.
M. Saiz, M. J. Alvarez-Cubero, J. C. Alvarez, and J. A. Lorente, “Forensic Genetics Against Children Trafficking: Missing Children Genetic Identification,” in Handbook of Missing Persons, Cham: Springer International Publishing, 2016, pp. 177–189. doi: 10.1007/978-3-319-40199-7_13.
R. J. Quinlan and E. H. Hagen, “New Genealogy: It’s Not Just for Kinship Anymore,” Field methods, vol. 20, no. 2, pp. 129–154, May 2008, doi: 10.1177/1525822X07314034.
M. Almuashi, S. Z. Mohd Hashim, D. Mohamad, M. H. Alkawaz, and A. Ali, “Automated kinship verification and identification through human facial images: a survey,” Multimed. Tools Appl., vol. 76, no. 1, pp. 265–307, 2017, doi: 10.1007/s11042-015-3007-5.
A. Durfey, “Leveraging AI and Genealogy for Family Reunification During Humanitarian Crises,” in Advanced Sciences and Technologies for Security Applications, 2025, pp. 357–368. doi: 10.1007/978-3-031-86997-6_11.
Q. Yuan and S. Xia, “Kinship Understanding for a Family Photo,” in 2019 Chinese Control And Decision Conference (CCDC), Jun. 2019, pp. 5319–5323. doi: 10.1109/CCDC.2019.8832876.
M. C. Mzoughi, N. Ben Aoun, and S. Naouali, “A review on kinship verification from facial information,” Vis. Comput., vol. 41, no. 3, pp. 1789–1809, Feb. 2025, doi: 10.1007/s00371-024-03493-1.
S. A. Khan, M. Ishtiaq, M. Nazir, and M. Shaheen, “Face recognition under varying expressions and illumination using particle swarm optimization,” J. Comput. Sci., vol. 28, pp. 94–100, Sep. 2018, doi: 10.1016/j.jocs.2018.08.005.
M. Chung, M. Wang, Z. Huang, and T. Okuyama, “Diverse sensory cues for individual recognition,” Dev. Growth Differ., vol. 62, no. 9, pp. 507–515, Dec. 2020, doi: 10.1111/dgd.12697.
T. Ojala, M. Pietikainen, and T. Maenpaa, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 7, pp. 971–987, Jul. 2002, doi: 10.1109/TPAMI.2002.1017623.
Xiaoyang Tan and B. Triggs, “Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions,” IEEE Trans. Image Process., vol. 19, no. 6, pp. 1635–1650, Jun. 2010, doi: 10.1109/TIP.2010.2042645.
T. Jabid, M. H. Kabir, and Oksam Chae, “Local Directional Pattern (LDP) for face recognition,” in 2010 Digest of Technical Papers International Conference on Consumer Electronics (ICCE), Jan. 2010, pp. 329–330. doi: 10.1109/ICCE.2010.5418801.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2016, vol. 2016-Decem, pp. 770–778. doi: 10.1109/CVPR.2016.90.
F. Dornaika, I. Arganda-Carreras, and O. Serradilla, “Transfer learning and feature fusion for kinship verification,” Neural Comput. Appl., vol. 32, no. 11, pp. 7139–7151, Jun. 2020, doi: 10.1007/s00521-019-04201-0.
M. A. Almuashi, S. Z. M. Hashim, N. Yusoff, and K. N. Syazwan, “A Fusion Schema of Hand-Crafted Feature and Feature Learning for Kinship Verification,” in Lecture Notes on Data Engineering and Communications Technologies, 2021, pp. 1050–1063. doi: 10.1007/978-3-030-70713-2_94.
L. R. Zuama, D. R. I. M. Setiadi, A. Susanto, S. Santosa, H.-S. Gan, and A. A. Ojugo, “High-Performance Face Spoofing Detection using Feature Fusion of FaceNet and Tuned DenseNet201,” J. Futur. Artif. Intell. Technol., vol. 1, no. 4, pp. 385–400, Feb. 2025, doi: 10.62411/faith.3048-3719-62.
V. Kumar and A. Purohit, “Tuned Attention-Guided Fusion of Deep and Handcrafted Features for Distinguishing AI-Generated and Human-Created Artworks,” J. Futur. Artif. Intell. Technol., vol. 2, no. 4, pp. 629–647, 2026, doi: 10.62411/faith.3048-3719-291.
X. Wu, X. Feng, C. Á. Casado, L. Liu, and M. B. López, “Exploring Facial Kinship Verification through Contactless Heart Activity Analysis,” in ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr. 2025, pp. 1–5. doi: 10.1109/ICASSP49660.2025.10888280.
J.-X. Jiang, H. Jing, L. Zhou, Y. Li, and Z. Wang, “Multi-attribute balanced dataset generation framework AutoSyn and KinFace Channel-Spatial Feature Extractor for kinship recognition,” Neurocomputing, vol. 613, p. 128750, Jan. 2025, doi: 10.1016/j.neucom.2024.128750.
I. Fibriani, E. M. Yuniarno, R. Mardiyanto, and M. H. Purnomo, “SSCNetViT: A Hybrid Siamese Sequential Classification-ViT Model for Kinship Recognition in Indonesia Facial Microexpression,” Int. J. Intell. Eng. Syst., vol. 18, no. 1, pp. 832–846, Feb. 2025, doi: 10.22266/ijies2025.0229.59.
M. Oruganti, T. Meenpal, and S. Majumder, “Kinship verification in childhood images using curvelet transformed features,” Comput. Electr. Eng., vol. 118, p. 109375, Aug. 2024, doi: 10.1016/j.compeleceng.2024.109375.
C. Yan and Y. Liu, “Kinship verification based on multi-scale feature fusion,” Multimed. Tools Appl., vol. 83, no. 40, pp. 88069–88090, Mar. 2024, doi: 10.1007/s11042-024-18879-5.
N. Nader, F. E.-Z. A. EL-Gamal, and M. Elmogy, “Enhanced kinship verification analysis based on color and texture handcrafted techniques,” Vis. Comput., vol. 40, no. 4, pp. 2325–2346, Apr. 2024, doi: 10.1007/s00371-023-02919-6.
A. Othmani, D. Han, X. Gao, R. Ye, and A. Hadid, “Kinship recognition from faces using deep learning with imbalanced data,” Multimed. Tools Appl., vol. 82, no. 10, pp. 15859–15874, Apr. 2023, doi: 10.1007/s11042-022-14058-6.
X. Zhu, C. Li, X. Chen, X. Zhang, and X.-Y. Jing, “Distance and Direction Based Deep Discriminant Metric Learning for Kinship Verification,” ACM Trans. Multimed. Comput. Commun. Appl., vol. 19, no. 1s, pp. 1–19, Feb. 2023, doi: 10.1145/3531014.
H. Kim, H. Kim, J. Shim, and E. Hwang, “A robust kinship verification scheme using face age transformation,” Comput. Vis. Image Underst., vol. 231, p. 103662, Jun. 2023, doi: 10.1016/j.cviu.2023.103662.
X. Chen et al., “Deep discriminant generation-shared feature learning for image-based kinship verification,” Signal Process. Image Commun., vol. 101, p. 116543, Feb. 2022, doi: 10.1016/j.image.2021.116543.
T. Karnik, P. Shivakumara, P. N. Chowdhury, U. Pal, T. Lu, and N. B. Anuar, “A new deep model for family and non-family photo identification,” Multimed. Tools Appl., vol. 81, no. 2, pp. 1765–1785, Jan. 2022, doi: 10.1007/s11042-021-11631-3.
M. Mukherjee, T. Meenpal, and A. Goyal, “FuseKin: Weighted image fusion based kinship verification under unconstrained age group,” J. Vis. Commun. Image Represent., vol. 84, p. 103470, Apr. 2022, doi: 10.1016/j.jvcir.2022.103470.
A. Abbas and M. Shoaib, “Kinship identification using age transformation and Siamese network,” PeerJ Comput. Sci., vol. 8, p. e987, Jun. 2022, doi: 10.7717/peerj-cs.987.
F. Liu, Z. Li, W. Yang, and F. Xu, “Age-Invariant Adversarial Feature Learning for Kinship Verification,” Mathematics, vol. 10, no. 3, p. 480, Feb. 2022, doi: 10.3390/math10030480.
J. P. Robinson, Z. Khan, Y. Yin, M. Shao, and Y. Fu, “Families in Wild Multimedia: A Multimodal Database for Recognizing Kinship,” IEEE Trans. Multimed., vol. 24, pp. 3582–3594, 2022, doi: 10.1109/TMM.2021.3103074.
Jiwen Lu, Xiuzhuang Zhou, Yap-Pen Tan, Yuanyuan Shang, and Jie Zhou, “Neighborhood Repulsed Metric Learning for Kinship Verification,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 36, no. 2, pp. 331–345, Feb. 2014, doi: 10.1109/TPAMI.2013.134.
S. Mahpod and Y. Keller, “Kinship verification using multiview hybrid distance learning,” Comput. Vis. Image Underst., vol. 167, pp. 28–36, Feb. 2018, doi: 10.1016/j.cviu.2017.12.003.
H. Wu, J. Chen, X. Liu, and J. Hu, “Component-based metric learning for fully automatic kinship verification,” J. Vis. Commun. Image Represent., vol. 79, p. 103265, Aug. 2021, doi: 10.1016/j.jvcir.2021.103265.
H. Yan, “Kinship verification using neighborhood repulsed correlation metric learning,” Image Vis. Comput., vol. 60, pp. 91–97, Apr. 2017, doi: 10.1016/j.imavis.2016.08.009.
M. Oruganti, T. Meenpal, and S. Majumder, “Easy pair selection method for Kinship Verification using fixed age group images,” Image Vis. Comput., vol. 136, p. 104727, Aug. 2023, doi: 10.1016/j.imavis.2023.104727.
S. Wang and H. Yan, “Discriminative sampling via deep reinforcement learning for kinship verification,” Pattern Recognit. Lett., vol. 138, pp. 38–43, Oct. 2020, doi: 10.1016/j.patrec.2020.06.019.
L. Zhang, Q. Duan, D. Zhang, W. Jia, and X. Wang, “AdvKin: Adversarial Convolutional Network for Kinship Verification,” IEEE Trans. Cybern., vol. 51, no. 12, pp. 5883–5896, Dec. 2021, doi: 10.1109/TCYB.2019.2959403.
S. Sun, Y. Yang, and H. Yan, “Kinship verification via Frequency Feature Decoupling and Fusion,” Pattern Recognit. Lett., vol. 193, pp. 1–7, Jul. 2025, doi: 10.1016/j.patrec.2025.04.002.
A. Nazari, O. Borzoei, and M. E. Moghaddam, “Kinship Verification through a Forest Neural Network,” arXiv. [Online]. Available: https://arxiv.org/abs/2504.18910
W.-T. Su, M.-H. Chen, C.-Y. Wang, S.-H. Lai, and T. Chen, “Kinship Representation Learning with Face Componential Relation,” in 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Oct. 2023, pp. 3097–3106. doi: 10.1109/ICCVW60793.2023.00335.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Munzza Bibi, Wakeel Ahmad, Syed M. Adnan, Asifa Bibi
This work is licensed under a Creative Commons Attribution 4.0 International License.
