Open Access iconOpen Access

ARTICLE

crossmark

A Deep Transfer Learning Approach for Addressing Yaw Pose Variation to Improve Face Recognition Performance

M. Jayasree1, K. A. Sunitha2,*, A. Brindha1, Punna Rajasekhar3, G. Aravamuthan3, G. Joselin Retnakumar1

1 Department of Electronics and Instrumentation Engineering, College of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Chennai, Tamil Nadu, 603203, India
2 Department of Electronics and Communication Engineering, SRM University, Amaravati, Mangalagiri, Andhra Pradesh, 522502, India
3 Security Electronics and Cyber Technology, Bhabha Atomic Research Centre, Anushakti Nagar, Mumbai, Maharashtra, 400085, India

* Corresponding Author: K. A. Sunitha. Email: email

Intelligent Automation & Soft Computing 2024, 39(4), 745-764. https://doi.org/10.32604/iasc.2024.052983

Abstract

Identifying faces in non-frontal poses presents a significant challenge for face recognition (FR) systems. In this study, we delved into the impact of yaw pose variations on these systems and devised a robust method for detecting faces across a wide range of angles from 0° to ±90°. We initially selected the most suitable feature vector size by integrating the Dlib, FaceNet (Inception-v2), and “Support Vector Machines (SVM)” + “K-nearest neighbors (KNN)” algorithms. To train and evaluate this feature vector, we used two datasets: the “Labeled Faces in the Wild (LFW)” benchmark data and the “Robust Shape-Based FR System (RSBFRS)” real-time data, which contained face images with varying yaw poses. After selecting the best feature vector, we developed a real-time FR system to handle yaw poses. The proposed FaceNet architecture achieved recognition accuracies of 99.7% and 99.8% for the LFW and RSBFRS datasets, respectively, with 128 feature vector dimensions and minimum Euclidean distance thresholds of 0.06 and 0.12. The FaceNet + SVM and FaceNet + KNN classifiers achieved classification accuracies of 99.26% and 99.44%, respectively. The 128-dimensional embedding vector showed the highest recognition rate among all dimensions. These results demonstrate the effectiveness of our proposed approach in enhancing FR accuracy, particularly in real-world scenarios with varying yaw poses.

Keywords


Cite This Article

APA Style
Jayasree, M., Sunitha, K.A., Brindha, A., Rajasekhar, P., Aravamuthan, G. et al. (2024). A deep transfer learning approach for addressing yaw pose variation to improve face recognition performance. Intelligent Automation & Soft Computing, 39(4), 745-764. https://doi.org/10.32604/iasc.2024.052983
Vancouver Style
Jayasree M, Sunitha KA, Brindha A, Rajasekhar P, Aravamuthan G, Retnakumar GJ. A deep transfer learning approach for addressing yaw pose variation to improve face recognition performance. Intell Automat Soft Comput . 2024;39(4):745-764 https://doi.org/10.32604/iasc.2024.052983
IEEE Style
M. Jayasree, K.A. Sunitha, A. Brindha, P. Rajasekhar, G. Aravamuthan, and G.J. Retnakumar "A Deep Transfer Learning Approach for Addressing Yaw Pose Variation to Improve Face Recognition Performance," Intell. Automat. Soft Comput. , vol. 39, no. 4, pp. 745-764. 2024. https://doi.org/10.32604/iasc.2024.052983



cc Copyright © 2024 The Author(s). Published by Tech Science Press.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 535

    View

  • 167

    Download

  • 0

    Like

Share Link