Journal of Soft Computing and Information Technology

Journal of Soft Computing and Information Technology

A Deep Face Detection Model with an Optimal Selection of Features Using the Firefly Optimization Algorithm

Document Type : Persian Original Article

Authors
Farnaz Hoseini
Masume Kheyri
Department of Computer Engineering, National University of Skills (NUS), Tehran, Iran.
10.22034/jscit.2025.509592.2109
Abstract
Today, facial recognition is an important issue in applications such as security systems, credit card control, and identification of criminals. The human face is inherently dynamic, continuously changing under the influence of various factors. For this reason, it is difficult to develop a computational model for face detection considering the complexity of faces and the multidimensional structure of vision. Therefore, face detection is known as a high-level activity in computer vision that can include many basic visualization techniques. In recent years, various techniques and methods have been presented for facial detection systems. Although the act of recognition from static images of faces has reached a high degree of reliability and efficiency, still increasing the accuracy of detection in face images is an important issue that can be investigated. In this study, a deep convolutional neural network is used to improve face detection. In the first stage of the proposed method, after selecting and extracting the primary data from the database, the necessary pre-processing is done on the images. The output of this step is given as input to the firefly optimization algorithm to be used to select effective features and recognize them for optimization. Finally, a deep convolutional neural network has been used in two steps of training and testing for face recognition. The purpose of presenting the proposed method is to increase the accuracy and reduce the computational complexity in the face detection process. The proposed method is implemented using MATLAB software and the implementation results show proper performance and increased accuracy in the diagnosis process. In the presented method, due to the optimal selection of features, a detection accuracy rate of 95.11 % has been obtained, which is higher than other methods presented in recent years. In addition, the recognition process in the proposed method is fast and can basically meet the requirements of real-time face detection.
Keywords
Face Detection
Optimal Feature Selection
Firefly Optimization Algorithm
Deep Convolutional Neural Network
[1] N. Nilsaz and M. Rastgarpour, “A new load-balancing algorithm using fuzzy logic and multi-objective firefly algorithm in cloud computing environment,” Journal of Soft Computing and Information Technology, vol. 10, no. 2, pp. 14–26, 2021.
[2] F. Hosseini and H. Sepehrzadeh, “Providing a face recognition system with an optimal selection of features based on the cuckoo optimization algorithm,” Iranian Journal of Electrical and Computer Engineering, vol. 1, no. 1, pp. 12–20, 2024.
[3] L. Li, X. Mu, S. Li, and H. Peng, “A review of face recognition technology,” IEEE Access, vol. 8, pp. 139110–139120, 2020.
[4] I. Adjabi, A. Ouahabi, A. Benzaoui, and A. Taleb-Ahmed, “Past, present, and future of face recognition: A review,” Electronics, vol. 9, no. 8, p. 1188, 2020.
[5] M. Zulfiqar, F. Syed, M. J. Khan, and K. Khurshid, “Deep face recognition for biometric authentication,” in Proc. Int. Conf. Electr., Commun. Comput. Eng. (ICECCE), Jul. 2019, pp. 1–6.
[6] A. V. Savchenko, “Facial expression and attributes recognition based on multi-task learning of lightweight neural networks,” in Proc. IEEE Int. Symp. Intell. Syst. Informat. (SISY), Sep. 2021, pp. 119–124.
[7] M. O. Oloyede, G. P. Hancke, and H. C. Myburgh, “A review on face recognition systems: recent approaches and challenges,” Multimedia Tools Appl., vol. 79, no. 37, pp. 27891–27922, 2020.
[8] X. S. Yang, “Firefly algorithms for multimodal optimization,” in Proc. Int. Symp. Stochastic Algorithms, 2009, pp. 169–178. Springer, Berlin, Heidelberg.
[9] M. Abdolhosseini, R. Abdollahi, and M. Rajaee, “Designing of PID controller for PMBLDC motor using metaheuristic algorithms,” Karafan Quarterly Scientific Journal, vol. 17, no. 4, pp. 147–161, 2021 (in Persian).
[10] F. Mohammadi, M. Molaei, and O. Afra, “Optimization of nuclear reactor power with control rods driven by switched reluctance motor (SRM) with differential evolution and firefly algorithms,” Karafan Quarterly Scientific Journal, vol. 17, no. 4, pp. 79–95, 2021 (in Persian).
[11] M. Hajarian, A. Shahbahrami, and F. Hoseini, “A parallel solution for the 0–1 knapsack problem using firefly algorithm,” in Proc. Conf. Swarm Intell. Evol. Comput. (CSIEC), Mar. 2016, pp. 25–30.
[12] H. N. Vu, M. H. Nguyen, and C. Pham, “Masked face recognition with convolutional neural networks and local binary patterns,” Applied Intelligence, vol. 52, no. 5, pp. 5497–5512, 2022.
[13] G. Revathy, K. B. Raj, A. Kumar, S. Adibatti, P. Dahiya, and T. M. Latha, “Investigation of E-voting system using face recognition using convolutional neural network (CNN),” Theoretical Computer Science, 2022.
[14] V. Jain and E. Learned-Miller, “FDDB: A benchmark for face detection in unconstrained settings,” UMass Amherst Technical Report, vol. 2, no. 4, p. 5, 2010.
[15] A. Banharnsakun, “Towards improving the convolutional neural networks for deep learning using the distributed artificial bee colony method,” International Journal of Machine Learning and Cybernetics, vol. 10, no. 6, pp. 1301–1311, 2019.
[16] N. Asha, A. S. Fiaz, J. Jayashree, J. Vijayashree, and J. Indumathi, “Principal component analysis on face recognition using artificial firefly swarm optimization algorithm,” Advances in Engineering Software, vol. 174, p. 103296, 2022.
[17] M. T. Islam, T. Ahmed, A. R. Rashid, T. Islam, M. S. Rahman, and M. T. Habib, “Convolutional neural network based partial face detection,” in Proc. IEEE 7th Int. Conf. Convergence Technol. (I2CT), Apr. 2022, pp. 1–6.
[18] D. Garg, P. Jain, K. Kotecha, P. Goel, and V. Varadarajan, “An efficient multi-scale anchor box approach to detect partial faces from a video sequence,” Big Data and Cognitive Computing, vol. 6, no. 1, p. 9, 2022.
[19] H. Yan, X. Wang, Y. Liu, Y. Zhang, and H. Li, “A new face detection method based on Faster RCNN,” in J. Phys.: Conf. Ser., vol. 1754, no. 1, p. 012209, Feb. 2021.
[20] P. Annamalai, “Automatic face recognition using enhanced firefly optimization algorithm and deep belief network,” International Journal of Intelligent Engineering & Systems, vol. 13, no. 5, 2020.
[21] H. Qin, J. Yan, X. Li, and X. Hu, “Joint training of cascaded CNN for face detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 3456–3465.
[22] S. S. Farfade, M. J. Saberian, and L. J. Li, “Multi-view face detection using deep convolutional neural networks,” in Proc. 5th ACM Int. Conf. Multimedia Retrieval, Jun. 2015, pp. 643–650.
[23] S. N. Makhadmeh, M. A. Al-Betar, I. A. Doush, M. A. Awadallah, S. Kassaymeh, S. Mirjalili, and R. A. Zitar, “Recent advances in Grey Wolf Optimizer, its versions and applications,” IEEE Access, vol. 12, pp. 22991–23028, 2023.
[24] M. Shehab, I. Mashal, Z. Momani, M. K. Y. Shambour, A. AL-Badareen, S. Al-Dabet, …, and L. Abualigah, “Harris hawks optimization algorithm: variants and applications,” Archives of Computational Methods in Engineering, vol. 29, no. 7, pp. 5579–5603, 2022.
[25] M. Guerrero-Luis, F. Valdez, and O. Castillo, “A review on the cuckoo search algorithm,” in Fuzzy Logic Hybrid Extensions of Neural and Optimization Algorithms: Theory and Applications, pp. 113–124, 2021.
Journal of Soft Computing and Information Technology
Volume 14, Issue 2
Summer - August
Summer 2025
Pages 1-17