Minimizing Number of Distinct Poses for Pose-Invariant Face Recognition

Carter Ung, Pranav Mantini, Shishir Shah

2025

Abstract

In unconstrained environments, extreme pose variations of the face are a long-standing challenge for person identification systems. The natural occlusion of necessary facial landmarks is notable to model performance degradation in face recognition. Pose-invariant models are data-hungry and require large variations of pose in training data to achieve comparable accuracy in recognizing faces from extreme viewpoints. However, data collection is expensive and time-consuming, resulting in a scarcity of facial datasets with large pose variations for model training. In this study, we propose a training framework to enhance pose-invariant face recognition by identifying the minimum number of poses for training deep convolutional neural network (CNN) models, enabling higher accuracy with minimum cost for training data. We deploy ArcFace, a state-of-the-art recognition model, as a baseline to evaluate model performance in a probe-gallery matching task across groups of facial poses categorized by pitch and yaw Euler angles. We perform training and evaluation of ArcFace on varying pose bins to determine the rank-1 accuracy and observe how recognition accuracy is affected. Our findings reveal that: (i) a group of poses at -45◦, 0◦, and 45◦yaw angles achieve uniform rank-1 accuracy across all yaw poses, (ii) recognition performance is better with negative pitch angles than positive pitch angles, and (iii) training with image augmentations like horizontal flips results in similar or better performance, further minimizing yaw poses to a frontal and 3 4 view.

Paper Citation

in Harvard Style

Ung C., Mantini P. and Shah S. (2025). Minimizing Number of Distinct Poses for Pose-Invariant Face Recognition. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 447-455. DOI: 10.5220/0013186400003912

in Bibtex Style

@conference{visapp25,
author={Carter Ung and Pranav Mantini and Shishir Shah},
title={Minimizing Number of Distinct Poses for Pose-Invariant Face Recognition},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={447-455},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013186400003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Minimizing Number of Distinct Poses for Pose-Invariant Face Recognition
SN - 978-989-758-728-3
AU - Ung C.
AU - Mantini P.
AU - Shah S.
PY - 2025
SP - 447
EP - 455
DO - 10.5220/0013186400003912
PB - SciTePress