An Intelligent Hybrid Feature-Engineering Approach for Covariant Face Recognition Using Deep Learning

Document Type : Research Paper

Authors

1 Research Scholar (Part Time), Research Centre - Department of Electronics and Communication Engineering, M. S. Ramaiah Institute of Technology, Bengaluru, India; Assistant Professor, Department of Electronics and Communication Engineering - M. S. Ramaiah Institute of Technology, Bengaluru, India.

2 Associate Professor, Department of Electronics and Communication Engineering, M. S. Ramaiah Institute of Technology, Bengaluru, India; Affiliated to Visvesvaraya Technological University, Belagavi-590018, Karnataka, India.

10.22059/jitm.2026.106256

Abstract

Face recognition (FR) is a non-contact biometric method integral to national and social security. It is pivotal in sectors like security, healthcare, banking, and criminal identification. Various techniques are being developed, including appearance and hybrid approaches, which either target specific facial features or consider the whole face for effective image recognition. This study explores hybrid machine learning techniques and enhanced covariates related to FR. The suggested approach is examined from a number of input viewpoints, including illumination, position variation, facial emotions, occlusions, and aging, which resulted in the widespread use of FR systems. The Generative Adversarial Network (GAN) is used to multiply the image on the dataset for image augmentation purposes. The facial covariants are extracted with the help of a hybrid feature engineering technique, such as a voting classifier that includes algorithms like K Nearest Neighbour, Support Vector Machine, and Random Forest Algorithm (KNN-SVM-RF). The dimension redundancy is achieved with the help of a combination of Principal Component Analysis and Independent Component Analysis algorithms. The modified VGG-16 algorithm is used to predict the image with the covariant similarity percentage of a person. Experiments conducted on the CelebFaces Attributes (CelebA) Dataset and Celebrity Face Image Dataset demonstrate that the hybrid strategy yields superior accuracy and robustness compared with CNN-only or classical approaches, achieving notable improvements in Precision, Recall, F1 score, and overall Accuracy.

Keywords

References

Ajlouni, N., Özyavaş, A., Ajlouni, F., Takaoğlu, F., & Takaoğlu, M. (2025). Enhanced hybrid facial emotion detection & classification. Franklin Open, 10, 100200.
Awaluddin, B. A., Chao, C. T., & Chiou, J. S. (2024). A hybrid image augmentation technique for user-and environment-independent hand gesture recognition based on deep learning. Mathematics, 12(9), 1393.
Elloumi, S., Bahroun, S., Yahia, S. B., & Kaddes, M. (2025). Enhanced Face Recognition in Crowded Environments with 2D/3D Features and Parallel Hybrid CNN-RNN Architecture with Stacked Auto-Encoder. Big Data and Cognitive Computing, 9(8), 191.
Ge, H., Zhu, Z., Ouyang, J., Ashraf, M. A., Qiu, Z., & Ibrahim, U. M. (2024). Integration of manifold learning and density estimation for fine-tuned face recognition. Symmetry, 16(6), 765.
Goel, A., Goel, A. K., & Kumar, A. (2023). The role of artificial neural network and machine learning in utilizing spatial information. Spatial Information Research, 31(3), 275-285.
Goel, R., Mehmood, I., & Ugail, H. (2021). A study of deep learning-based face recognition models for sibling identification. Sensors, 21(15), 5068.
Gui, J., Sun, Z., Wen, Y., Tao, D., & Ye, J. (2021). A review on generative adversarial networks: Algorithms, theory, and applications. IEEE transactions on knowledge and data engineering, 35(4), 3313-3332.
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. In Proceedings of the IEEE international conference on computer vision workshops (pp. 142-150).
Kong, J., Wang, H., Yang, C., Jin, X., Zuo, M., & Zhang, X. (2022). A spatial feature-enhanced attention neural network with high-order pooling representation for application in pest and disease recognition. Agriculture, 12(4), 500.
Lin, N., Ding, Y., & Tan, Y. (2025). Optimization design and application of library face recognition access control system based on improved PCA. Plos one, 20(1), e0313415.
Lu, D., & Yan, L. (2021). [Retracted] face detection and recognition algorithm in digital image based on computer vision sensor. Journal of Sensors, 2021(1), 4796768.
Nayak, J. S., & Indiramma, M. (2022). An approach to enhance age invariant face recognition performance based on gender classification. Journal of King Saud University-Computer and Information Sciences, 34(8), 5183-5191.
Niu, H., Qiu, Y., Li, M., Zhou, G., Hu, J., & Zhan, X. (2022). When to trust your simulator: Dynamics-aware hybrid offline-and-online reinforcement learning. Advances in Neural Information Processing Systems, 35, 36599-36612.
Rajpal, A., Sehra, K., Bagri, R., & Sikka, P. (2023). Xai-fr: explainable ai-based face recognition using deep neural networks. Wireless Personal Communications, 129(1), 663-680.
Rusia, M. K., & Singh, D. K. (2023). A comprehensive survey on techniques to handle face identity threats: challenges and opportunities. Multimedia Tools and Applications, 82(2), 1669-1748.
Sa, J., Ryu, J., & Kim, H. (2025). ECTFormer: An efficient Conv-Transformer model design for image recognition. Pattern Recognition, 159, 111092.
Sarker, I. H. (2021). Machine learning: Algorithms, real-world applications and research directions. SN computer science, 2(3), 1-21.
Sekhar, J. C., Josephson, P. J., Chinnasamy, A., Maheswari, M., Sankar, S., & Kalangi, R. R. (2025). Automated face recognition using deep learning technique and center symmetric multivariant local binary pattern. Neural Computing and Applications, 37(1), 263-281.
Shanmugam, M., Viswanatha, V. M., & Raja, K. B. (2024). Precise Face Recognition through GWO-Cuckoo Optimized Neural Networks and MRMR Feature Selection from Compressed Hybrid Domain Fusion. International Journal of Intelligent Engineering & Systems, 17(1).
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Singh, P., Kansal, M., Singh, R., Kumar, S., & Sen, C. (2024). A hybrid approach based on Haar Cascade, Softmax, and CNN for human face recognition: a hybrid approach for human face recognition. Journal of Scientific & Industrial Research (JSIR), 83(4), 414-423.
Tagmatova, Z., Umirzakova, S., Kutlimuratov, A., Abdusalomov, A., & Im Cho, Y. (2025). A hyper-attentive multimodal transformer for real-time and robust facial expression recognition. Applied Sciences, 15(13), 7100.
Tao, Z. (2024). Face recognition detection based on deep learning. Journal of Combinatorial Mathematics and Combinatorial Computing, 127, 2651-2658.
Wu, Q., Chen, Y., & Meng, J. (2020). DCGAN-based data augmentation for tomato leaf disease identification. IEEE access, 8, 98716-98728.
Yang, F., Liu, R., & Zhu, D. (2025). Pedestrian dynamics modeling and social force analysis based on object detection. Frontiers in Physics, 13, 1579280.
Journal of Information Technology Management
Volume 18, Issue 1
2026
Pages 102-122

Files

Share

How to cite

Statistics