Omer Abdulhaleem Naser, Sharifah Mumtazah Syed Ahmad, Khairulmizam Samsudin and Marsyita Hanafi
Adv. Artif. Intell. Mach. Learn., 3 (2):1039-1055
1. Omer Abdulhaleem Naser: A final-year Ph.D. student at the University Putra Malaysia, Faculty of Engineering. I majored in computational methods in engineering. The specified research field is biometrics, particularly facial recognition for occluded faces.
2. Sharifah Mumtazah Syed Ahmad: Department of Computer and Communication System Engineering, Faculty of Engineering, University Putra Malaysia (UPM), Serdang, Malaysia
3. Khairulmizam Samsudin: Department of Computer and Communication System Engineering, Faculty of Engineering, University Putra Malaysia (UPM), Serdang, Malaysia
4. Marsyita Hanafi: Department of Computer and Communication System Engineering, Faculty of Engineering, University Putra Malaysia (UPM), Serdang, Malaysia
DOI: 10.54364/AAIML.2023.1162
Article History: Received on: 18-Apr-23, Accepted on: 12-May-23, Published on: 29-May-23
Corresponding Author: Omer Abdulhaleem Naser
Email: omar.abdulhalem592@gmail.com
Citation: Omer Abdulhaleem Naser, et al. Investigating the Impact of Yaw Pose Variation on Facial Recognition Performance. Advances in Artificial Intelligence and Machine Learning. 2023;3(2):62.
Facial recognition systems often struggle with
detecting faces in poses that deviate from the frontal view. Therefore, this
paper investigates the impact of variations in yaw poses on the accuracy of
facial recognition systems and presents a robust approach optimized to detect
faces with pose variations ranging from 0° to ±90°. The proposed system
integrates MTCNN, FaceNet, and SVC, and is trained and evaluated on the Taiwan
dataset, which includes face images with diverse yaw poses. The training
dataset consists of 89 subjects, with approximately 70 images per subject, and
the testing dataset consists of 49 subjects, each with approximately 5 images.
Our system achieved a training accuracy of 99.174% and a test accuracy of
96.970%, demonstrating its efficiency in detecting faces with pose variations.
These findings suggest that the proposed approach can be a valuable tool in
improving facial recognition accuracy in real-world scenarios.