POSE-Inclusive Face Recognition:‎ Addressing The Influence of Face Angle in ‎Person Identification

  • Authors

    • C J Harshitha Dept. of Computer Applications ‎JSS Science and Technology University Mysuru, India
    • R. K. Bharathi Dept. of Computer Applications ‎JSS Science and Technology University Mysuru, India
    • Rakshitha P Dept. of Computer Applications ‎JSS Science and Technology University Mysuru, India
    https://doi.org/10.14419/0jt7m549

    Received date: June 18, 2025

    Accepted date: July 17, 2025

    Published date: July 27, 2025

  • Occluded Face Recognition; MTCNN; CNN

  • Abstract

    Face recognition remains a critical task in computer vision, ‎especially in applications involving authentication, surveillance, ‎and access control. However, real-world challenges like pose ‎variations and occlusions continue to hinder recognition ‎performance. This paper presents a pose-inclusive face ‎recognition system that integrates Multi-task Cascaded ‎Convolutional Networks (MTCNN) for face detection and ‎alignment with ResNet-50 for feature extraction and ‎classification. The Labeled Faces in the Wild (LFW) dataset is ‎used, and images undergo data augmentation and normalization ‎to simulate pose diversity. Experimental evaluation ‎demonstrates that ResNet-50 significantly outperforms ‎traditional CNN models, achieving an accuracy of 99.60%. The ‎proposed approach ensures robust and scalable performance ‎in uncontrolled environments‎.

  • References

    1. Santemiz, P., Spreeuwers, L. J., & Veldhuis, R. N. J. (2024). A survey on automatic face recognition using side-view face images. IET Biometrics, 2024(1), Article 7886911. https://doi.org/10.1049/2024/7886911.
    2. Rusia, M. K., Singh, D. K., & Ansari, M. A. (2024). A novel deep transfer learning-based approach for face pose estimation. Cybernetics and In-formation Technologies, 24(2), 105–119. https://doi.org/10.2478/cait-2024-0018.
    3. Naser, O. A., Syed Ahmad, S. M., Samsudin, K., & Hanafi, M. (2024). Enhancing 2D face recognition systems: Addressing yaw poses and occlu-sions with masks, glasses, and both. Advances in Artificial Intelligence and Machine Learning, 4(3), 2545–2574. https://doi.org/10.54364/AAIML.2024.43149.
    4. Schroff, F., Kalenichenko, D., & Philbin, J. (2015). FaceNet: A unified embedding for face recognition and clustering. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 815–823. https://doi.org/10.1109/CVPR.2015.7298682.
    5. Na, I. S., Tran, C., Nguyen, D., & Dinh, S. (2020). Facial UV map completion for pose-invariant face recognition: A novel adversarial approach based on coupled attention residual UNets. Journal of Ambient Intelligence and Humanized Computing, 11(6), 2461–2472. https://doi.org/10.1186/s13673-020-00250-w.
    6. Hu, W. (2023). Improving 2D face recognition via fine-level facial depth generation and RGB-D complementary feature learning. arXiv.2305.04426arXiv.
    7. Kim, M., Su, Y., Liu, F., Jain, A., & Liu, X. (2024). KeyPoint relative position encoding for face recognition. Proceedings of the IEEE/CVF Con-ference on Computer Vision and Pattern Recognition (CVPR), 244–255. https://doi.org/10.1109/CVPR52733.2024.00031.
    8. Ruan, S., Tang, C., Zhou, X., Jin, Z., Chen, S., Wen, H., Liu, H., & Tang, D. (2020). Multi-pose face recognition based on deep learning in uncon-strained scenes. Applied Sciences, 10(13), 4669. https://doi.org/10.3390/app10134669.
    9. Essel, J. K., Mensah, J. A., Ocran, E., & Asiedu, L. (2024). On the search for efficient face recognition algorithm subject to multiple environ-mental constraints. Heliyon, 10(7), Article e28568. https://doi.org/10.1016/j.heliyon.2024.e28568.
    10. Tsai, E.-J., & Yeh, W.-C. (2021). PAM: Pose Attention Module for pose-invariantfacerecognition.arXiv.
    11. Meng, Q., Xu, X., Wang, X., Qian, Y., Qin, Y., Wang, Z., Zhao, C., Zhou, F., & Lei, Z. (2021). PoseFace: Pose-invariant features and pose-adaptive loss for face recognition. arXiv.
    12. Pitteri, G., Munaro, M., & Menegatti, E. (2017). Depth-based frontal view generation for pose invariant face recognition with consumer RGB-D sensors. In Intelligent Autonomous Systems 14 (pp. 925–937). Springer. https://doi.org/10.1007/978-3-319-48036-7_67.
    13. Cao, K., Rong, Y., Li, C., Tang, X., & Loy, C. C. (2018). Pose-robust face recognition via deep residual equivariant mapping. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, 1085–1094.
    14. Ge, S., Li, C., Zhao, S., & Zeng, D. (2020). Occluded face recognition in the wild by identity-diversity inpainting. IEEE Transactions on Circuits and Systems for Video Technology, 30(10), 3387–3397. https://doi.org/10.1109/TCSVT.2020.2967754.
    15. Cen, F., & Qi, G.-J. (2018). Dictionary representation of deep features for occlusion-robust face recognition. IEEE Access, 6, 73925–73934.
    16. Neto, P. C., Boutros, F., Pinto, J. R., Damer, N., Sequeira, A. F., & Cardoso, J. S. (2021). Focus Face: Multi-task contrastive learning for masked face recognition. Proceedings of the 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), 1–8. https://doi.org/10.1109/FG52635.2021.9666792.
    17. Noyes, E., Davis, J. P., Petrov, N., Gray, K. L. H., & Ritchie, K. (2021). The effect of face masks and sunglasses on identity and expression recognition with super-recognizers and typical observers. Royal Society Open Science, 8(3), Article 201169. https://doi.org/10.1098/rsos.201169.
    18. Naser, O. A., Mumtazah, S., Hanafi, M., & Samsudin, K. (2024). Enhancing 2D face recognition systems: Addressing yaw poses and occlusions with masks, glasses, and both. Multimedia Tools and Applications, 83(5), 1–26. https://doi.org/10.54364/AAIML.2024.43149.
    19. Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019). ArcFace: Additive angular margin loss for deep face recognition. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4690–4699. https://doi.org/10.1109/CVPR.2019.00482.
    20. Cament, L. A., Galdames, F. J., Bowyer, K. W., & Pérez, C. A. (2015). Face recognition under pose variation with local Gabor features enhanced by Active Shape and Statistical Models. Pattern Recognition, 48(11), 3371–3384. https://doi.org/10.1016/j.patcog.2015.05.017.
    21. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vi-sion and Pattern Recognition (CVPR), 770–778. https://doi.org/10.1109/CVPR.2016.90.
    22. Huang, G. B., Jain, V., & Learned-Miller, E. (2007). Labeled faces in the wild: A database for studying face recognition in unconstrained envi-ronments. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 1–8.
    23. Zhang, K., Zhang, Z., Li, Z., & Qiao, Y. (2016). Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Sig-nal Processing Letters, 23(10), 1499–150. https://doi.org/10.1109/LSP.2016.2603342.

  • Downloads

  • How to Cite

    Harshitha, C. J. ., Bharathi, R. K. ., & P, R. . (2025). POSE-Inclusive Face Recognition:‎ Addressing The Influence of Face Angle in ‎Person Identification. International Journal of Basic and Applied Sciences, 14(3), 311-316. https://doi.org/10.14419/0jt7m549