Volume 17 , Issue 2 , PP: 01-13, 2026 | Cite this article as | XML | Html | PDF | Full Length Article
Ali F. Rashid 1 , Ilyas Khudhair Yalwi 2 , Ali Hakem Alsaeedi 3 , Riyadh Rahef Nuiaa Alogaili 4 * , Mazin Abed Mohammed 5
Doi: https://doi.org/10.54216/JCIM.170201
Face recognition in unconstrained environments is difficult due to varying poses and lighting conditions. This can severely impair the performance of intelligent recognition models. Traditional methods often do not adapt well to these variations, which results in poor performance and limited applicability. This paper proposes a hybrid intelligent face recognition model based on hierarchical feature extraction and illumination normalization (H-FR). The proposed method employs a hierarchical feature extraction model to capture macro and micro facial details, ensuring reliable recognition across diverse poses and lighting conditions. Employing Adaptive Histogram Equalization on the A and B channels of the LAB colour space effectively normalizes illumination variations, enhancing the visibility and consistency of facial features. The proposed model has been tested and validated on the "Pins Face Recognition" dataset available on Kaggle, which encompasses various celebrity faces captured in varying poses and lighting conditions. The proposed model has been demonstrated through extensive experimentation to outperform AlexNet and VGG-19. The compared algorithms achieved accuracies of 88% for AlexNet and 93% for VGG-19, while the proposed H-FR model achieved 96%.
Face Recognition , Hybrid Feature extraction , Machine learning , Lumination Normalization , Edge enhancement
[1] S. Bhat, K. L. Narayan, and N. Lavanya, "Survey on object detection, face tracking, digital mapping and lane following for remotely piloted aerial systems (RPAS)," Int. J. Hum. Comput. Intell, vol. 2, no. 2, pp. 94-105, 2023.
[2] S. K. Shivthare, Y. K. Sharma, and R. D. Patil, "Multimodal biometric in computer vision," in Multimodal Biometric and Machine Learning Technologies: Applications for Computer Vision. IGI Global, 2023, pp. 1-29.
[3] J. Ren, S. Zhang, and S. Liu, "Significance and implications of nanoparticle–biological corona fingerprints in diagnosis, prognosis, and therapeutics for diverse disorders," Nanoscale, vol. 15, no. 27, pp. 11422-11433, 2023.
[4] M. Khatri and A. Sharma, "Deep learning approach based on iris, face, and palmprint fusion for multimodal biometric recognition system," Int. J. Performability Eng., vol. 19, no. 6, 2023.
[5] S. Alfoudi, A. H. Alsaeedi, M. H. Abed, A. M. Otebolaku, and Y. S. Razooqi, "Palm vein identification based on hybrid feature selection model," Int. J. Intell. Eng. Syst., vol. 14, no. 5, pp. 469-478, 2021.
[6] F. E. El Orche et al., "Taphonomical security: DNA information with a foreseeable lifespan," in Proc. Int. Conf. Cryptol. Inform. Secur. Latin Amer., 2021, pp. 674-694.
[7] Z. Li, K. Chen, S. Li, and T. T. Liu, "Expert consensus on ECG identification applied in the insurance industry," Cardiovasc. Innov. Appl., vol. 8, no. 1, p. 20230061, 2023.
[8] M. Rukhiran, S. Wong-In, and P. Netinant, "User acceptance factors related to biometric recognition technologies of examination attendance in higher education: TAM model," Sustainability, vol. 15, no. 4, p. 3092, 2023.
[9] T. A. Kadhim, W. Hariri, N. S. Zghal, and D. Ben Aissa, "A face recognition application for Alzheimer's patients using ESP32-CAM and Raspberry Pi," J. Real-Time Image Process., vol. 20, no. 5, p. 100, 2023.
[10] M. R. Hasan, R. Guest, and F. Deravi, "Presentation-level privacy protection techniques for automated face recognition - A survey," ACM Comput. Surv, 2023.
[11] P. M. Azhar, S. K. S. K. Rahman, and M. A. A. Hossain, "An efficient deep learning framework for face recognition using hybrid features," Int. J. Image Process., vol. 14, no. 1, pp. 1-12, 2023, doi: 10.5121/ijip.2023.14101.
[12] P. Naveen, "Occlusion-aware facial expression recognition: A deep learning approach," Multimedia Tools Appl., pp. 1-27, 2023.
[13] L. Li, X. L. Qiu, M. L. Jing, and S. S. Pu, "Block compressed sensing image reconstruction via untrained network priors," IAENG Int. J. Comput. Sci., vol. 50, no. 2, 2023.
[14] H. Alsaeedi, Y. Alazzawi, and S. M. Hadi, "Fast dust sand image enhancement based on color correction and new fuzzy intensification operators," Int. J. Innov. Comput, vol. 13, no. 1-2, pp. 31-35, 2022.
[15] S. M. Hadi et al., "Trigonometric words ranking model for spam message classification," IET Netw., 2022.
[16] 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.
[17] F. Liu, D. Chen, F. Wang, Z. Li, and F. Xu, "Deep learning based single sample face recognition: A survey," Artif. Intell. Rev., vol. 56, no. 3, pp. 2723-2748, 2023.
[18] M. Karpagam et al., "A novel face recognition model for fighting against human trafficking in surveillance videos and rescuing victims," Soft Comput., vol. 27, no. 18, pp. 13165-13180, 2023.
[19] M. S. Bilkhu, S. Gupta, and V. K. Srivastava, "Emotion classification from facial expressions using cascaded regression trees and SVM," in Proc. Int. Conf. Adv. Comput. Commun. Syst., 2021, pp. 585-594.
[20] M. Ali and D. Kumar, "A combination between deep learning for feature extraction and machine learning for recognition," in 2021 12th Int. Conf. Comput. Commun. Netw. Technol. (ICCCNT), 2021, pp. 1-6.
[21] Y. M. Saib and S. Pudaruth, "Is face recognition with masks possible?" Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 7, 2021.
[22] A. Nandi, V. Mehta, R. Jairaj, D. Charan, and S. K. Sharma, "Deep learning based surveillance system for tracking unknown faces and movements," in Proc. IEEE Int. Conf. Consum. Electron. (ICCE), 2022, pp. 1-5.
[23] P. S. Chandran et al., "Missing child identification system using deep learning and multiclass SVM," in Proc. Int. Conf. Adv. Comput. Commun. Syst., 2021, pp. 113-116.
[24] M. Usgan, R. Ferdiana, and I. Ardiyanto, "Deep learning pre-trained model as feature extraction in facial recognition for identification of electronic identity cards by considering age progressing," in IOP Conf. Ser., Mater. Sci. Eng., vol. 1115, no. 1, 2021, p. 012034.
[25] A. J. J. G. A. B. S. Adnan, M. I. M. N. Ahmed, and S. A. M. Rahman, "Deep learning-based framework for facial emotion recognition: A survey," J. Ambient Intell. Humaniz. Comput, vol. 15, no. 5, pp. 4517-4530, 2024, doi: 10.1007/s12652-023-04567-8.
[26] B. Ma and Y. Chen, "Attentive enhanced convolutional neural network for point cloud analysis," IAENG Int. J. Comput. Sci., vol. 50, no. 2, 2023.
[27] Y. L. Fu, W. Song, W. Xu, J. Lin, and X. Nian, "Feature recognition in multiple CNNs using sEMG images from a prototype comfort test," Comput. Methods Programs Biomed, p. 107897, 2023.
[28] S. S. Chakravarthi, B. Rao, N. P. Challa, R. Ranjana, and A. Rai, "Gesture recognition for enhancing human computer interaction," J. Sci. Ind. Res., vol. 82, no. 4, pp. 438-443, 2023.
[29] G. Rajeshkumar et al., "Smart office automation via faster R-CNN based face recognition and internet of things," Meas., Sensors, vol. 27, p. 100719, 2023.
[30] H. Zhong, C. Huang, X. Zhang, and M. Pan, "Metaverse CAN: Embracing continuous, active, and non-intrusive biometric authentication," IEEE Netw., 2023.
[31] H. S. H. A. Aljohani, A. A. Alzahrani, and A. A. Alzahrani, "Face recognition system using deep learning techniques: A review," J. King Saud Univ. - Comput. Inf. Sci., vol. 36, no. 5, pp. 1141-1153, 2024, doi: 10.1016/j.jksuci.2022.03.005.
[32] A. Saleem, S. Paheding, N. Rawashdeh, A. Awad, and N. Kaur, "A non-reference evaluation of underwater image enhancement methods using a new underwater image dataset," IEEE Access, vol. 11, pp. 10412-10428, 2023.
[33] R. Ali et al., "A comprehensive survey on face recognition techniques based on deep learning," J. Vis. Commun. Image Represent., vol. 90, p. 103956, 2023, doi: 10.1016/j.jvcir.2022.103956.
[34] J. Ferdinand, C. Wijaya, A. N. Ronal, I. S. Edbert, and D. Suhartono, "ATM security system modeling using face recognition with FaceNet and Haar cascade," in 2022 6th Int. Conf. Inform. Comput. Sci. (ICICoS), 2022, pp. 111-116.
