Nomadic Pastoralist Optimization Algorithm for Enhanced Convolutional Neural Networks in Face Recognition

Abdulrazaq A. A., Abdulrazaq M. B., Ibrahim Y., Adedokun E. A.

Abstract


Face recognition (FR) remains a prominent focus in computer vision research, with convolutional neural networks (CNNs) widely recognized for their efficiency in this domain. Achieving optimal performance from CNNs requires fine-tuning their parameters, which can be challenging and time-consuming when done manually. To address this, population-based metaheuristic methods offer an automated approach to hyperparameter optimization, significantly reducing manual effort while enhancing model efficiency. This study employs the Nomadic Pastoralist Optimization Algorithm (NPOA) to optimize CNN hyperparameters for face recognition. Key parameters such as learning rate, batch size, the number of filters, dropout rate and dense units are fine-tuned using NPOA. Experiments conducted on a standard FR dataset demonstrate that the proposed NPOA-CNN model achieves superior accuracy compared to existing CNN models. Through iterative optimization, NPOA effectively minimizes the objective function by selecting the best combination of hyperparameters. As a result, the proposed model achieves an impressive face recognition accuracy of 98.82%.


Full Text:

PDF

References


Abdullahi, I. M., Mu’azu, M. B., Olaniyi, O. M., & Agajo, J. (2019). A novel cultural evolution-based nomadic pastoralist optimization algorithm (NPOA): the mathematical models. 2019 2nd International Conference of the IEEE Nigeria Computer Chapter (NigeriaComputConf),

Abdullahi, I. M., Mu’azu, M. B., Olaniyi, O. M., & Agajo, J. (2021). Pastoralist Optimization Algorithm (POA): A Culture-Inspired Metaheuristic for Uncapacitated Facility Location Problem (UFLP). Hybrid Intelligent Systems: 20th International Conference on Hybrid Intelligent Systems (HIS 2020), December 14-16, 2020,

Agarwal, R., Jain, R., Regunathan, R., & Pavan, K. C. S. (2019). Automatic attendance system using face recognition technique. Proceedings of the 2nd International Conference on Data Engineering and Communication Technology: ICDECT 2017,

Alzubaidi, L., Zhang, J., Humaidi, A. J., Al‑Dujaili, A., Duan, Y., Al‑Shamma, O., Santamaría, J., Fadhel, M. A., Al‑Amidie, M., & Laith Farhan, L. (2021). Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal on Big Data, 3(53), 1-72. https://doi.org/10.1186/s40537-021-00444-8

Bacanin, N., Bezdan, T., Tuba, E., Strumberger, I., & Tuba, M. (2020). Optimizing CNN hyperparameter by enhanced swarm intelligence metaheuristics. Algorithms, 13(67), 1-33. https://doi.org/10.3390/a13030067

Bergstra, J., & Bengio, Y. (2012). Random search for hyper-parameter optimization. Journal of machine learning research, 13(2).

Hu, G., Yang, Y., Yi, D., Kittler, J., Christmas, W., Li, S. Z., & Hospedales, T. (2015). When face recognition meets with deep learning: an evaluation of convolutional neural networks for face recognition. Proceedings of the IEEE international conference on computer vision workshops,

Ilyas, B. R., Mohammed, B., Khaled, M., &, & Miloud, K. (2019). Enhanced face recognition system based on deep CNN. 2019 6th International Conference on Image and Signal Processing and their Applications (ISPA),

Karlupia, N., Mahajan, P., Abrol, P., & Lehana, P. K. (2023). A genetic algorithm based optimized convolutional neural network for face recognition. International Journal of Applied Mathematics and Computer Science, 33(1).

Kortli, Y., Jridi, M., Al Falou, A., & Atri, M. (2020). Face recognition systems: A survey. Sensors, 20(2), 342.

Mikolaj, W., Zaneta, S., Gertych, S. K., & Arkadiusz, G. (2024). Improving classification accuracy of fine turned CNN model impact of hyperparameter Optimization. Heliyon 10, 1-11. https://doi.org/10.1016/j.heliyon.2024.e26586

Mittal, S., & Patel, S. (2023). Age Invariant Face Recognition Techniques: A Survey on the Recent Developments, Challenges and Potential Future Directions. International Journal of Engineering Trends and Technology 71 (5), 435-460. https://doi.org/https://doi.org/10.14445/22315381/IJETT-V71I5P243

Nurhopipah, A., & Larasati, N. A. (2021). CNN Hyperparameter optimiztion using random grid coarse to fine seach for face classification. Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, 6(1), 19-26. https://doi.org/10.22219/kinetik.v6i1.1185

Vose, A., Balma, J., Heye, A., Rigazzi, A., Siegel, C., Moise, D., Robbins, B., & Sukumar, R. (2019). Recombination of artificial neural networks. arXiv preprint arXiv:1901.03900.

Wang, Y., Zhang, H., & Zhang, G. (2019). cPSO-CNN: An efficient PSO-based algorithm for fine-tuning hyper-parameters of convolutional neural networks. Swarm and Evolutionary Computation, 49, 114-123.

Wu, J., Chen, X., Zhang, H., Xiong, L., Lei, H., & Deng, S. (2019). Hyperparameter optimization for machine learning models based on Bayesian optimization. Journal of Electronic Science and Technology, 17(1), 26-40.

Yang, L., & Shami, A. (2020). On hyperparameter optimization of machine learning algorithms: Theory and practice. Neurocomputing, 415, 295-316.

Zulfiqar, M., Syed, F., Khan, M. J., & Khurshid, K. (2019). Deep face recognition for biometric authentication. 2019 international conference on electrical, communication, and computer engineering (ICECCE).


Refbacks

  • There are currently no refbacks.