International Journal of Computational and Electronic Aspects in Engineering
Volume 7 · Issue 2 · June 2026 · pp. 268-277
Article · Peer Reviewed
Received: April 08, 2026 · Accepted: June 10, 2026 · Published: June 25, 2026
DOI: 10.26706/ijceae.7.2.20260315
Open Access · CC BY 4.0

Skeleton Identification for Gender Estimation Using Computer Vision Techniques

Nagham Salim Mohammed*
New Renewable Energy, Science, Mosul, Nineveh, Iraq.

*Corresponding author: nagham.salim@uomosul.edu.iq
Download PDF Cite this article Certificate Volume 7 Issue 2

Abstract

One of the most important tasks in forensic anthropology is the determination of biological sex in the skeleton. This study aims to develop and evaluate an automated and objective computational framework for biological sex determination in the field of forensic anthropology. The suggested computational model uses a set of pre-trained computer vision techniques to automatically extract deep anatomical features from skull computed tomography (CT). Then, the ReliefF algorithm is used for feature selection and SVMs and wide neural networks are employed for classification. The data consisted of CT images obtained from the database of 424 patients (219 males and 205 females), whose ages ranged from 22 to 68 years. The three architectures tested were AlexNet, ResNet-101, and EfficientNet-B0 and were used as deep feature extractors from their fully connected layers. Based on the outcomes of the experiment, it is evident that the EfficientNet-B0 model, when combined with the cubic SVM classifier, provided the most successful results with overall accuracy of 96.4%, 96.1% in recognizing males and 96.8% in recognizing females. The systematic study of the impact of reducing the number of features showed that reducing the number of features to 100 using the ReliefF method gave 95.0% accuracy in classification, which is 1.4% lower than the one obtained when working with the full set (1000 features). The results indicate that a limited subset of deep features contains strong discriminative information for classification. The present research provides a highly reliable and objective tool for the identification of gender in forensic medicine.

Keywords

Forensic gender estimation Skull computed tomography Computer Vision Network Support Vector Machines Forensic anthropology

References

  1. T. V. Oommen, "Moisture equilibrium in cellulose insulation," IEEE Electrical Insulation Magazine, vol. 19, no. 2, pp. 17–23, 2003.
  2. Intergovernmental Panel on Climate Change (IPCC), Climate Change 2021: The Physical Science Basis, Cambridge, U.K.: Cambridge University Press, 2021.
  3. IEEE Power and Energy Society, IEEE Std C57.91-2011: IEEE Guide for Loading Mineral-Oil-Immersed Transformers and Step-Voltage Regulators, IEEE, 2012. doi: 10.1109/IEEESTD.2012.6166922 .
  4. M. Wang, X. Zhang, J. Li, and Y. Chen, "Deep learning-based fault diagnosis for power transformers: A review," IEEE Access, vol. 9, pp. 120345–120367, 2021. doi: 10.1109/ACCESS.2021.3101234 .
  5. A. Abu-Siada and S. Islam, "A review of dissolved gas analysis in transformer diagnosis," IEEE Electrical Insulation Magazine, vol. 28, no. 3, pp. 35–44, 2012. doi: 10.1109/MEI.2012.6190039 .
  6. B. García, J. C. Burgos, and Á. Alonso, "Transformer tank vibration modeling for the detection of winding displacements," IEEE Transactions on Power Delivery, vol. 21, no. 1, pp. 157–163, Jan. 2006. doi: 10.1109/TPWRD.2005.852370 .
  7. S. M. Ghoneim, "Intelligent fault diagnosis techniques for power transformers using artificial intelligence: A review," Energies, vol. 14, no. 19, Art. no. 6128, 2021. doi: 10.3390/en14196128 .
  8. J. Faiz and B. M. Ebrahimi, Transformer Condition Monitoring and Diagnosis, Singapore: Springer, 2018. doi: 10.1007/978-981-10-6031-2 .
  9. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet classification with deep convolutional neural networks," in Advances in Neural Information Processing Systems (NeurIPS), vol. 25, pp. 1097–1105, 2012.
  10. N. Gozzi, E. Giacomello, M. Sollini, M. Kirienko, A. Ammirabile, P. Lanzi, et al., "Image embeddings extracted from CNNs outperform other transfer learning approaches in classification of chest radiographs," Diagnostics, vol. 12, no. 9, p. 2084, 2022. doi: 10.3390/diagnostics12092084 .
  11. N. K. Younis, M. H. Qahtan, and M. R. Ahmed, "A review of artificial intelligence techniques for medical image enhancement," International Journal of Computational and Electronic Aspects in Engineering, vol. 6, no. 2, pp. 98–107, Jun. 2025.
  12. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778, 2016. doi: 10.1109/CVPR.2016.90 .
  13. F. Khozeimeh, D. Sharifrazi, N. H. Izadi, J. H. Joloudari, A. Shoeibi, R. Alizadehsani, et al., "Combining a random forest-based algorithm with CNN features to diagnose COVID-19," Scientific Reports, vol. 12, no. 1, pp. 1–12, 2022.
  14. M. Tan and Q. V. Le, "EfficientNet: Rethinking model scaling for convolutional neural networks," in Proceedings of the 36th International Conference on Machine Learning (ICML), vol. 97, pp. 6105–6114, 2019. Available: https://proceedings.mlr.press/v97/tan19a.html .
  15. M. W. Ahdi, A. Kunaefi, B. A. Nugroho, and A. Yusuf, "Convolutional neural network (CNN) EfficientNet-B0 model architecture for paddy diseases classification," in Proceedings of the 14th International Conference on Information and Communication Technology and Systems (ICTS), pp. 105–110, 2023.
  16. I. Manole, A.-I. Butacu, R. N. Bejan, and G.-S. Tiplica, "Enhancing dermatological diagnostics with EfficientNet: A deep learning approach," Bioengineering, vol. 11, no. 8, p. 810, 2024. doi: 10.3390/bioengineering11080810 .
  17. Y. Tian, Y. Shi, and X. Liu, "Recent advances on support vector machines research," Technological and Economic Development of Economy, vol. 18, no. 1, pp. 5–33, 2012.
  18. C. Cortes and V. Vapnik, "Support-vector networks," Machine Learning, vol. 20, no. 3, pp. 273–297, 1995. doi: 10.1007/BF00994018 .
  19. G. Sangar and V. Rajasekar, "Optimized classification of potato leaf disease using EfficientNet-LITE and KE-SVM in diverse environments," Frontiers in Plant Science, vol. 16, p. 1499909, 2025. doi: 10.3389/fpls.2025.1499909 .
  20. M. Bukhari, S. Yasmin, S. Sammad, A. A. Abd El-Latif, and H. Tao, "Efficient breast cancer mammograms diagnosis using three deep neural networks and term variance," Journal of King Saud University – Computer and Information Sciences, vol. 35, no. 1, pp. 36–45, 2023. doi: 10.1016/j.jksuci.2022.12.002 .
  21. L. Torrey and J. Shavlik, "Transfer learning," in Handbook of Research on Machine Learning Applications and Trends, Hershey, PA, USA: IGI Global, 2010, pp. 242–264.
  22. S. Adap et al., "Classifying histopathologic glioblastoma sub-regions with EfficientNet," arXiv preprint, arXiv:2511.08896, 2024.
  23. A. Masood, B. Sheng, P. Li, X. Hou, X. Wei, J. Qin, et al., "Lung cancer classification in histopathology images using multiresolution EfficientNets," Applied Sciences, vol. 13, no. 20, p. 11442, 2023. doi: 10.3390/app132011442 .
  24. M. Hamdan, M. Omer, and A. Hamdan, "Isolated convolutional-neural-network-based deep-feature extraction for brain tumor classification using shallow classifier," Computational Intelligence and Neuroscience, vol. 2022, Art. no. 3967668, 2022. doi: 10.1155/2022/3967668 .
  25. T. M. Kadhim, "Deep convolutional neural network–based image processing for automated mammography analysis and breast cancer detection," International Journal of Computational and Electronic Aspects in Engineering, vol. 6, no. 4, pp. 243–251, Dec. 2025. doi: 10.26706/ijceae.6.4.20250904 .
  26. M. Obert, D. Schulze, R. Sader, and M. A. Verhoff, "Age and gender-dependent bone density changes of the human skull disclosed by high-resolution flat-panel computed tomography," International Journal of Legal Medicine, vol. 125, no. 3, pp. 417–425, 2011. doi: 10.1007/s00414-010-0544-3 .
  27. I. Afrianty, D. Nasien, M. R. A. Kadir, and H. Haron, "Determination of gender from pelvic bones and patella in forensic anthropology: A comparison of classification techniques," in Proceedings of the 1st International Conference on Artificial Intelligence, Modelling and Simulation (AIMS), pp. 3–7, 2014. doi: 10.1109/AIMS.2013.9 .
  28. S. Braun, N. Schwendener, F. Kanz, S. Lösch, and M. Milella, "What we see is what we touch? Sex estimation on the skull in virtual anthropology," International Journal of Legal Medicine, vol. 138, no. 5, pp. 2113–2125, 2024. doi: 10.1007/s00414-024-03244-w .
  29. S. K. Ghanim, "Hybrid ResNet50 and DenseNet121 with adaptive weighted feature fusion in infectious chest diseases classification," International Journal of Computational and Electronic Aspects in Engineering, vol. 7, no. 2, pp. 211–226, Jun. 2026. doi: 10.26706/ijceae.7.2.20260310 .
  30. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998. doi: 10.1109/5.726791 .
  31. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet classification with deep convolutional neural networks," Communications of the ACM, vol. 60, no. 6, pp. 84–90, 2017. doi: 10.1145/3065386 .
  32. M. Shafiq and Z. Gu, "Deep residual learning for image recognition: A survey," Applied Sciences, vol. 12, no. 18, p. 8972, 2022. doi: 10.3390/app12188972 .
  33. M. Tan and Q. V. Le, "EfficientNet: Rethinking model scaling for convolutional neural networks," arXiv preprint, arXiv:1905.11946, 2020.
  34. J. Cervantes, F. Garcia-Lamont, L. Rodríguez-Mazahua, and A. Lopez, "A comprehensive survey on support vector machine classification: Applications, challenges and trends," Neurocomputing, vol. 408, pp. 189–215, 2020. doi: 10.1016/j.neucom.2019.10.118 .
  35. S. Islam, Samsuzzaman, M. N. Reza, K. H. Lee, S. Ahmed, Y. J. Cho, N. D. Hoh, and S. O. Chung, "Image processing and support vector machine (SVM) for classifying environmental stress symptoms of pepper seedlings grown in a plant factory," Agriculture, vol. 12, no. 12, p. 2142, 2022. doi: 10.3390/agriculture12122142 .
  36. R. J. Urbanowicz, M. Meeker, W. La Cava, R. S. Olson, and J. H. Moore, "Relief-based feature selection: Introduction and review," Journal of Biomedical Informatics, vol. 85, pp. 189–203, 2018. doi: 10.1016/j.jbi.2018.07.014 .
  37. M. Sokolova and G. Lapalme, "A systematic analysis of performance measures for classification tasks," Information Processing & Management, vol. 45, no. 4, pp. 427–437, 2009. doi: 10.1016/j.ipm.2009.03.002 .
  38. D. M. W. Powers, "Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation," Journal of Machine Learning Technologies, vol. 2, no. 1, pp. 37–63, 2011.
  39. T. Fawcett, "An introduction to ROC analysis," Pattern Recognition Letters, vol. 27, no. 8, pp. 861–874, 2006. doi: 10.1016/j.patrec.2005.10.010 .
  40. E. B. Fowlkes and C. L. Mallows, "A method for comparing two hierarchical clusterings," Journal of the American Statistical Association, vol. 78, no. 383, pp. 553–569, 1983. doi: 10.1080/01621459.1983.10478008 .
  41. D. Chicco, M. J. Warrens, and G. Jurman, "The Matthews correlation coefficient (MCC) is more informative than Cohen's kappa and Brier score in binary classification assessment," IEEE Access, vol. 9, pp. 78368–78381, 2021. doi: 10.1109/ACCESS.2021.3084050 .
  42. D. Chicco and G. Jurman, "The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation," BMC Genomics, vol. 21, p. 6, 2020. doi: 10.1186/s12864-019-6413-7 .