Intelligent Data Analysis, volume 28, issue 1, pages 377-392

Robust partial face recognition using multi-label attributes

Gaoli Sang 1
Zeng Dan 2
Chao Yan 3, 4
Raymond Veldhuis 5, 6
Luuk Spreeuwers 5
Publication typeJournal Article
Publication date2024-02-03
Q3
Q4
SJR0.322
CiteScore2.2
Impact factor0.9
ISSN1088467X, 15714128
Artificial Intelligence
Theoretical Computer Science
Computer Vision and Pattern Recognition
Abstract

Partial face recognition (PFR) is challenging as the appearance of the face changes significantly with occlusion. In particular, these occlusions can be due to any item and may appear in any position that seriously hinders the extraction of discriminative features. Existing methods deal with PFR either by training a deep model with existing face databases containing limited occlusion types or by extracting un-occluded features directly from face regions without occlusions. Limited training data (i.e., occlusion type and diversity) can not cover the real-occlusion situations, and thus training-based methods can not learn occlusion robust discriminative features. The performance of occlusion region-based method is bounded by occlusion detection. Different from limited training data and occlusion region-based methods, we propose to use multi-label attributes for Partial Face Recognition (Attr4PFR). A novel data augmentation is proposed to solve limited training data and generate occlusion attributes. Apart from occlusion attributes, we also include soft biometric attributes and semantic attributes to explore more rich attributes to combat the loss caused by occlusions. To train our Attr4PFR, we propose an implicit attributes loss combined with a softmax loss to enforce Attr4PFR to learn discriminative features. As multi-label attributes are our auxiliary signal in the training phase, we do not need them in the inference. Extensive experiments on public benchmark AR and IJB-C databases show our method is 3% and 2.3% improvement compared to the state-of-the-art.

Found 

Are you a researcher?

Create a profile to get free access to personal recommendations for colleagues and new articles.
Metrics
Share
Cite this
GOST |
Cite this
GOST Copy
Sang G. et al. Robust partial face recognition using multi-label attributes // Intelligent Data Analysis. 2024. Vol. 28. No. 1. pp. 377-392.
GOST all authors (up to 50) Copy
Sang G., Zeng Dan, Yan C., Veldhuis R., Spreeuwers L. Robust partial face recognition using multi-label attributes // Intelligent Data Analysis. 2024. Vol. 28. No. 1. pp. 377-392.
RIS |
Cite this
RIS Copy
TY - JOUR
DO - 10.3233/ida-227309
UR - https://doi.org/10.3233/ida-227309
TI - Robust partial face recognition using multi-label attributes
T2 - Intelligent Data Analysis
AU - Sang, Gaoli
AU - Zeng Dan
AU - Yan, Chao
AU - Veldhuis, Raymond
AU - Spreeuwers, Luuk
PY - 2024
DA - 2024/02/03
PB - IOS Press
SP - 377-392
IS - 1
VL - 28
SN - 1088-467X
SN - 1571-4128
ER -
BibTex |
Cite this
BibTex (up to 50 authors) Copy
@article{2024_Sang,
author = {Gaoli Sang and Zeng Dan and Chao Yan and Raymond Veldhuis and Luuk Spreeuwers},
title = {Robust partial face recognition using multi-label attributes},
journal = {Intelligent Data Analysis},
year = {2024},
volume = {28},
publisher = {IOS Press},
month = {feb},
url = {https://doi.org/10.3233/ida-227309},
number = {1},
pages = {377--392},
doi = {10.3233/ida-227309}
}
MLA
Cite this
MLA Copy
Sang, Gaoli, et al. “Robust partial face recognition using multi-label attributes.” Intelligent Data Analysis, vol. 28, no. 1, Feb. 2024, pp. 377-392. https://doi.org/10.3233/ida-227309.
Found error?