Abstract

Background: Facial biometrics play a critical role in cybercrime investigations, digital identity verification, and surveillance-based forensic systems. Despite their widespread use, many artificial intelligence (AI)–driven facial recognition pipelines operate without biologically validated craniofacial feature foundations, raising concerns regarding interpretability, bias, and forensic reliability. Aim: This study aims to establish a biologically grounded framework for AI-assisted forensic facial analysis by examining the inheritance, stability, and predictability of live craniofacial anthropometric traits across three biological generations of Indian families. Methods: A total of 216 individuals from 48 Indian families spanning three generations were examined. Fourteen standardized craniofacial dimensions were recorded using calibrated vernier callipers under natural head position. Trait normalization, intergenerational comparisons, heritability estimation, transfer score analysis, and machine-learning–based predictability assessment were performed using robust statistical modeling and AI-assisted analytical techniques. Result: Craniofacial traits exhibited uneven hereditary patterns. Vertical craniofacial dimensions demonstrated greater generational resemblance, biological stability, and algorithmic predictability compared to horizontal traits. Sto-Sl, En-Ex, and ZyZy emerged as highly stable and orensically reliable craniofacial features with strong heritability and predictive performance. Conclusion: The study provides a statistically validated and biologically explainable reference framework for AI-based facial analysis in cyber and digital forensic applications. By anchoring AI models to biologically stable craniofacial traits, the findings enhance the reliability, interpretability, and forensic admissibility of facial evidence.

• 1.   Seselj, M., Duren, D.L., Sherwood, R.J., et al. (2015). Heritability of the human craniofacial complex. The Anatomical Record, 298(9), 1535–1547. (DOI: 10.1002/ar.23186)
• 2.   Adekunle, A.A., et al. (2021). Facial anthropometry measurements using 3D stereophotogrammetry. Journal of Craniofacial Surgery, 32(5), 1800–1806. (DOI: 10.1097/ SCS.0000000000008036 )
• 3.   Richmond, S., et al. (2018). Craniofacial genetics and phenotypic variation. Orthodontics & Craniofacial Research, 21(1), 1–9.
• 4.   Naqvi, S., et al. (2021). Shared heritability of human face and brain shape. Nature Communications, 12, 1–11. ( https://doi. org/10.1038/s41588-021-00827-w )
• 5.   Bishara, S.E. (1995). Changes in facial dimensions assessed from lateral and frontal photographs. American Journal of Orthodontics and Dentofacial Orthopedics, 108(4), 389–393.
• 6.   Johannsdottir, B., Thorarinsson, F., Thoradarson, A., & Magnusson, T. E. (2005). Heritability of craniofacial characteristics between parents and offspring estimated from lateral cephalograms. American Journal of Orthodontics and Dentofacial 385 Orthopedics, 127(2), 200–207.
• 7.   Krishnan, A., & Rattani, A. (2023). A novel approach for bias mitigation of gender classification algorithms using consistency regularization. Image and Vision Computing, 137, 104793. https://doi.org/10.1016/j. imavis.2023.104793
• 8.   Lin, Y.C., Miyazono, H., Ichinose, M., & Nakasima, A. (1998). A study to evaluate the parent-offspring similarity in the maxillofacial profile using fingerprints in Japanese families. Journal of Craniofacial Genetics and Developmental Biology, 18(2), 119–127.
• 9.   Mossey, P.A. (1999). The heritability of malocclusion: Part 2. The influence of genetics in malocclusion. British Journal of Orthodontics, 26(3), 195–203
• 10.   DeepFakes and beyond: A survey of face manipulation and fake detection. arXiv preprint arXiv:2001.00179.
• 11.   Krishan K., Kanchan T. Measurement Error in Anthropometric Studies and its Significance in Forensic Casework. Ann Med Health Sci Res. 2016 Jan-Feb; 6(1): 62-3. doi: 10.4103/2141- 9248.180277. PMID: 27144080; PMCID: PMC4849120..
• 12.   Bours, P., & Mondal, S. (2021). Biometric triage in cyber investigations. Digital Investigation, 38, 301–309.
• 13.   Koseoglu, M., Ramachandran, R.A., Ozdemir, H., Ariani, M.D., Bayindir, F., & Sukotjo, C. (2024). Automated facial landmark measurement using machine learning: A feasibility study. Journal of Prosthetic Dentistry, 134(4), 1148–1155. https://doi. org/10.1016/j.prosdent.2024.04.007
• 14.   Sharma, P., & Verma, P. (2024). Computational forensics & ML for intergenerational craniofacial analysis. Conference/Manuscript.
• 15.   Miller, S.A., & Brown, T. (2022). Deep fake detection in forensic science. Forensic Science International, 335, 111223.
• 16.   Hajian-Tilaki K. (2013). Receiver Operating Characteristic (ROC) Curve Analysis for Medical Diagnostic Test Evaluation. Caspian166 Indian Journal of Forensic Medicine and Pathology IJFMP/Volume 19 Number 2 April–June 2026 journal of internal medicine, 4(2), 627–635.
• 18.   Porto, L.F., Lima, L.N.C., Franco, A., Pianto, D., Machado, C.E.P., & De Barros Vidal, F. (2020). Estimating sex and age from a face: a forensic approach using machine learning based on photo-anthropometric indexes of the Brazilian population. International Journal of Legal Medicine, 134(6), 2239–2259. https:// doi.org/10.1007/s00414-020-02346-5
• 19.   Seselj, M., et al. (2019). Heritability of craniofacial traits in family-based samples. Annals of Human Biology, 46(6), 453–461. (doi: 10.1002/ar.23186 )
• 20.   White, J.D., et al. (2021). Genetic architecture of facial morphology. Nature Genetics, 53, 130– 138. ( doi: 10.1038/s41588-020-00741-7)
• 21.   Sharma, R. (2024). Sexual dimorphism in facial heights: A comprehensive study of Indian adults. African Journal of Biomedical Research, 1960–1964. https://doi.org/10.53555/ajbr. v27i4s.3972
• 22.   Patel, J.R., & Mehta, A. (2022). Inheritance patterns of craniofacial traits in South Asian populations. Forensic Anthropology, 5(3), 210–221.
• 23.   Lahoti, S.K., Karia, A.M., & Lahoti, K.B. (2013). Heritability of Facial Characteristics between Parents and Offsprings: A Photographic Study. The Journal of Indian Orthodontic Society, 47, 419–425. https://doi.org/10.5005/jpjournals-10021-1199
• 24.   Stephan, C.N., & Caple, J. (2018). Reliability of facial landmarks in forensic practice. Journal of Forensic Identification, 68(2), 145–160. (https://doi.org/10.1080/20961790.2018.15 19892)
• 25.   Weinberg, S.M., Naidoo, S., Govier, D.P., Martin, R.A., Kane, A.A., & Marazita, M.L. (2006). Anthropometric precision and accuracy of Digital Three-Dimensional photogrammetry. Journal of Craniofacial Surgery, 17(3), 477– 483. https://doi.org/10.1097/00001665- 200605000-00015
• 26.   Benjamini, Y., Drai, D., Elmer, G., Kafkafi, N., & Golani, I. (2001). Controlling the false discovery rate in behavior genetics research. Behavioural brain research, 125(1-2), 279–284. https://doi. org/10.1016/s0166-4328(01)00297-2
• 27.   Baydaş, B., Erdem, A., Yavuz, I., & Ceylan, I. (2007). Heritability of facial proportions and soft-tissue profile characteristics in Turkish Anatolian siblings. American Journal of Orthodontics and Dentofacial Orthopedics, 131(4), 504–509.
• 28.   Adekunle, A.A., et al. (2021). Validation of 3D facial anthropometry for forensic applications. Forensic Science International, 321, 110741.
• 29.   Saini, H., et al. (2022). AI-based biometric profiling in cybercrime. Journal of Cybersecurity, 8(1), tyac012.
• 30.   Alves, Y.B. (2021) et al. Photoanthropometry as a method of facial analysis: A systematic review. Research, Society and Development, 10(14), e22101421637.(DOI: https://doi. org/10.33448/rsd-v10i2.12469)