Face recognition is one of the most prominent applications of computer vision and pattern recognition, with wide-ranging use in security systems, biometric identification, and human–computer interaction. Despite significant advances in deep learning, traditional methods that combine feature extraction and machine learning classification remain valuable for achieving high accuracy with lower computational complexity. This research focuses on developing a robust face recognition system using Histogram of Oriented Gradients (HOG) for feature extraction and Support Vector Machine (SVM) for classification. The proposed model employs the HOG descriptor to capture edge orientations and intensity gradients from facial images, producing distinctive feature vectors that effectively represent facial structures under varying lighting and pose conditions. These features are then fed into an SVM classifier, which separates facial identities based on optimized hyperplane boundaries. The system was trained and tested on benchmark facial datasets, including LFW (Labeled Faces in the Wild) and ORL, to evaluate performance under diverse conditions. Experimental results demonstrate that the HOG–SVM combination achieve good accuracy, outperforming conventional PCA and LDA-based methods while maintaining computational efficiency. The findings confirm that integrating HOG features with an SVM classifier offers a balanced trade-off between accuracy, speed, and resource efficiency, making it suitable for real-time face recognition applications in constrained environments such as surveillance systems and mobile authentication. Future work will explore the integration of deep feature embeddings with HOG–SVM models to further enhance adaptability and robustness in complex scenarios.

The face recognition with Histogram of Oriented Gradients (HOG) and Support Vector Machines (SVM) has proven to be a highly effective approach for face recognition tasks. HOG’s ability to extract robust and discriminative features from face images, coupled with SVM’s powerful classification capabilities, enables accurate identification of individuals even in varying lighting conditions and pose. The HOG+SVM framework has demonstrated excellent performance in face recognition benchmarks, outperforming other state-of-the-art methods. Its robustness, efficiency, and accuracy make it a suitable solution for various applications, including security, surveillance, and identity verification systems. Overall, the HOG+SVM approach has contributed significantly to the advancement of face recognition technology, paving the way for further innovations in this field.

[1]T.-H. Tsai, C.-C. Huang, C.-H. Chang, and M. A. Hussain, ‘‘Design of wireless vision sensor network for smart home,’’ [2]K. Muhammad, J. Ahmad, I. Mehmood, S. Rho, and S. W. Baik, ‘‘Convolutional neural networks based Fire detection in surveillance videos,’’ [3]M. T. Bhatti, M. G. Khan, M. Aslam, and M. J. Fiaz, ‘‘Weapon detection in real-time CCTV videos using deep learning,’’ [4]A. Krizhevsky, I. Sutskever, and G. E. Hinton, ‘‘ImageNet classification with deep convolutional neural networks,’’ [5]J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, ‘‘You only look once: Unified, real-time object detection,’’ [6]S. W. Shah and S. S. Kanhere, ‘‘Recent trends in user authentication— A survey,’’ [7]K. M. Renuka, S. Kumari, D. Zhao, and L. Li, ‘‘Design of a secure password-based authentication scheme for M2M networks in IoT enabled cyber-physical systems,’’ [8]H.-J. Mun, ‘‘Biometric Information and OTP based on authentication mechanism using blockchain,’’ J. Converg. Inf. Technol [9]A. Mohammed Ali and A. Kadhim Farhan, ‘‘A novel improvement with an effective expansion to enhance the MD5 hash function for verification of a secure E-Document,’’ [10]H.-J. Mun, S. Hong, and J. Shin, ‘‘A novel secure and efficient hash function with extra padding against rainbow table attacks,’’ Cluster Comput., vol. 21 [11]J. Shin, Z. Liu, C. M. Kim, and H.-J. Mun, ‘‘Writer identification using intra-stroke and inter-stroke information for security enhancements in P2P systems,’’ Peer-to-Peer Netw. Appl. [12]Sattibabu, D., Varsha Deepika, K., Santhi Kumari, K., Sai Rahul Tej, A., Nalajala, P. (2024). Tracing Missing Person Through Facial Recognition Using Deep Learning. SCI 2024. Lecture Notes in Networks and Systems, vol 1147. Springer, Singapore. https://doi.org/10.1007/978-981-97-7880-5_24

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close