Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{189769,
        author = {Dr. Rohan K. Naik},
        title = {Side View Face Recognition Using Deep Learning Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {8},
        pages = {749-753},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189769},
        abstract = {Face recognition systems have achieved impressive performance in controlled environments and frontal-face conditions. However, recognizing faces from side-view or profile images remains a significant challenge due to severe pose variations, self-occlusion of facial features, and loss of discriminative information. In real-world scenarios such as surveillance and forensic investigations, face images are often captured at non-frontal angles, making conventional face recognition systems less effective.
This research presents a comprehensive deep learning-based framework for robust side-view face recognition. The proposed system integrates pose-aware preprocessing, deep feature extraction using Convolutional Neural Networks (CNNs), and metric learning-based classification to achieve pose-invariant facial representations. Extensive experiments conducted on multiple benchmark datasets demonstrate that the proposed approach significantly improves recognition accuracy for side-view and extreme profile faces compared to traditional and baseline deep learning methods.},
        keywords = {Side View Face Recognition, Pose Variation, Deep Learning, CNN, Metric Learning},
        month = {December},
        }