Dynamic Liveness-Integrated CNN Architecture for Face-Iris Spoof Detection

References

[1] Abdalla, M. A., Abdo, A. A., and Lawgali, A. O., “Utilizing discrete wavelet transform and discrete cosine transform for iris recognition,” in Proc. 20th Int. Conf. Sci. Tech. Autom. Control Comput. Eng. (STA), 2020, pp. 283–286.

[2] Abdo, A., El-Tarhouni, W., Younus, W., and Abraheem, A., “Iris recognition system based on fuzzy local binary pattern histogram and multiple classifiers,” in Proc. IEEE 2nd Int. Maghreb Meeting MI-STA, 2022, pp. 452–457.

[3] Abdo, A. A., Lawgali, A., and Zohdy, A. K., “Iris recognition based on histogram equalization and discrete cosine transform,” in Proc. 6th Int. Conf. Eng. MIS, 2020, pp. 1–5.

[4] Abikoye, O. C., Ojo, U. A., Awotunde, J. B., and Ogundokun, R. O., “A safe and secured iris template using steganography and cryptography,” Multimedia Tools and Applications, vol. 79, no. 31–32, pp. 23483–23506, 2020.

[5] Abo-Zaid, A., Haggag, A., Kasban, H., and Eltokhy, M. A. R., “Multimodal biometric scheme for human authentication technique based on voice and face recognition fusion,” Multimedia Tools and Applications, vol. 78, pp. 24077–24099, 2018.

[6] Shibel, S., Liu, Y., Yu, S., and Chen, K., “Deep learning detection of facial biometric presentation attack using ResNet-50 and majority voting,” IEEE Access, vol. 10, pp. 32730–32741, 2022.

[7] Schardosim, D. F. A., Sandberg, D. F. A., and Trevisan, A., “Presentation attack detection using imaging and liveness attributes,” J. Intell. Syst., 2019.

[8] Zhou, Y., Guo, G., Cao, Z., and Yang, J., “Improved softmax loss for deep learning‐based face and expression recognition,” Pattern Recognit. Lett., vol. 139, pp. 145–151, 2019.

[9] Soleymani, A., Neshatian, K., and Zhang, M., “Multi-level feature abstraction from CNNs for multimodal biometric identification,” Pattern Recognit., vol. 79, pp. 172–183, 2018.

[10] Al-Waisy, A. S., Al-Fahdawi, S., Al-Fahdawi, O., Al-Zobaidi, S., and Muhammad, G., “A multimodal biometric system for personal identification based on deep learning approaches,” Neurocomputing, vol. 210, pp. 116–128, 2016.

[11] Alay, K., and Al-Baity, M., “Multimodal biometric fusion using CNN and deep score fusion,” J. Comput. Sci., vol. 16, no. 3, pp. 233–245, 2020.

[12] Jenkins, M., Li, C., Cheng, J., and Wu, S., “Using deep learning techniques and genetic-based feature extraction for presentation attack mitigation,” Expert Syst. Appl., vol. 160, pp. 113–118, 2020.

[13] Safavipour, M., Nasrabadi, N., and Pourreza, H., “Deep hybrid multimodal biometric recognition system based on feature-level fusion of five biometric traits,” IEEE Access, vol. 11, pp. 114580–114592, 2023.

[14] Hamd, M., and Mohammed, H., “Multimodal biometric system based on face–iris feature level fusion,” Int. J. Comput. Appl., vol. 182, no. 12, pp. 1–6, 2019.

[15] Ammour, K., Boudraa, M., and Attia, R., “Face–iris multimodal biometric identification using hybrid fusion,” J. Electr. Syst. Inf. Technol., vol. 7, no. 1, pp. 1–9, 2020.

[16] Shi, P., Hoque, S., and Deravi, F., “An attention-guided framework for explainable biometric presentation attack detection,” Sensors, vol. 22, no. 9, p. 3365, 2022.

[17] Minaee, S., and Abdolrashidi, A., “Deepiris: Iris recognition using a deep learning approach,” arXiv preprint arXiv:1907.09380, 2019.

[18] Nguyen, K., Fookes, C., Ross, A., and Sridharan, S., “Iris recognition with off-the-shelf CNN features: A deep learning perspective,” IEEE Access, vol. 6, pp. 18848–18855, 2018.

[19] Nguyen, K., Fookes, C., Sridharan, S., and Senior, L., “Constrained design of deep iris networks,” IEEE Trans. Image Process., vol. 29, pp. 7166–7175, 2020.

[20] Omran, M., and AlShemmary, E. N., “An iris recognition system using deep convolutional neural network,” J. Phys.: Conf. Ser., vol. 1530, p. 012159, 2020.

[21] Sujana, M., “Weighted fusion approach for multi-modal biometric recognition system using deep networks,” Int. J. Innov. Technol. Explor. Eng., vol. 9, no. 3, pp. 771–777, 2020.

[22] Borra, S., Malyala, V. V. S., and Murthy, R. S., “Face recognition using convolutional neural networks,” Int. J. Sci. Eng. Technol., vol. 8, no. 1, pp. 1–4, 2020.

[23] Shalaby, A. S., Gad, R., Hemdan, E. E., and El-Fishawy, N., “An efficient CNN-based encrypted iris recognition approach in cognitive-IoT system,” Multimedia Tools Appl., 2021.

[24] Mehmood, A., and Mishra, B., “A survey on various unimodal biometric techniques,” Sparklinglight Trans. Artif. Intell. Quantum Comput., vol. 1, no. 1, pp. 23–35, 2021.

[25] Shende, P., and Dandwate, Y. H., “Convolutional neural network-based multimodal biometric human authentication using face, palm veins, and fingerprint,” Int. J. Innov. Technol. Explor. Eng., vol. 9, no. 3, pp. 771–777, 2020.

[26] Mulyadi, I., et al., “Intelligent security system based on biometric face recognition,” J. Theor. Appl. Inf. Technol., vol. 101, no. 17, pp. 1–10, 2023.

[27] Jin, Q., et al., “Deep learning for biometric fusion using CNNs,” Appl. Sci., vol. 9, no. 21, p. 4574, 2019.

[28] Sheena, S., and Mathew, S., “CNN-based iris recognition system: A novel approach,” Proc. ISMAC-CVB, 2020.

[29] Ogbuokiri, B. O., and Agu, M. N., “An enhanced authentication system using face and fingerprint technologies,” IOSR J. Comput. Eng., vol. 17, no. 6, pp. 74–84, 2015.

[30] Alhasan, M. J., Abdulhussein, S. M., and Khwayyir, A. H. K., “Fingerprint positioning of user devices in LTE cellular networks using k-nearest neighbour algorithm,” Int. J. Electr. Comput. Eng., vol. 11, no. 1, pp. 528–535, 2021

@article{1710350,
      author = {Afolabi Awodeyi, Philip Asuquo, Bliss Stephen},
      title = {Dynamic Liveness-Integrated CNN Architecture for Face-Iris Spoof Detection},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {9},
      number = {2},
      pages = {1079-1089},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1710350.pdf},
      abstract = {This study addresses the critical vulnerability of biometric systems to spoofing and presentation attacks by proposing a secure, CNN-integrated anti-spoofing framework for multimodal face and iris recognition. The purpose of the research is to enhance the reliability of biometric authentication systems by embedding dynamic liveness detection directly into the recognition pipeline. The system leverages physiological cues such as eye blinking, temporal texture variations, and pupil motion, which are difficult to replicate in spoof media like printed images and video replays. A dual-branch CNN architecture is employed to extract both spatial and temporal features from face and iris inputs. These features are fused with liveness indicators to improve decision accuracy. Synthetic spoofing attacks were introduced into the ORL and CASIA-IrisV4 datasets to simulate real-world adversarial conditions, including high-resolution photo and video-based attacks. The model was trained and evaluated using standard biometric security metrics. Results show that the proposed system achieves a spoof detection accuracy of 98.9%, with a false acceptance rate (FAR) of 0.00% and a false rejection rate (FRR) of 1.1%. Compared to baseline CNN models without liveness integration, the framework significantly improves resilience against spoofing. In conclusion, the integration of dynamic liveness cues into CNN-based multimodal recognition enhances both security and reliability, making the system suitable for deployment in high-assurance access control environments and offering a foundation for future mobile or edge-based biometric solutions.},
      keywords = {Anti-spoofing, Liveness detection, CNN, Face-Iris biometrics, Presentation attack detection},
      month = {August},
  }