Learning from Partially Occluded Faces

Fares Al-Qunaieer, Mohamed Alkanhal

2016

Abstract

Although face recognition methods in controlled environments have achieved high accuracy results, there are still problems in real-life situations. Some of the challenges include changes in face expressions, pose, lighting conditions or presence of occlusion. There were several efforts for tackling the occlusion problem, mainly by learning discriminating features from non-occluded faces for occluded faces recognition. In this paper, we propose the reversed process, to learn from the occluded faces for the purpose of non-occluded faces recognition. This process has several useful applications, such as in suspects identification and person re-identification. Correlation filters are constructed from training images (occluded faces) images of each person, which are used later for the classification of input images (non-occluded faces). In addition, the use of skin masks with the correlation filters is investigated.

Paper Citation

in Harvard Style

Al-Qunaieer F. and Alkanhal M. (2016). Learning from Partially Occluded Faces . In Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-173-1, pages 534-539. DOI: 10.5220/0005665605340539

in Bibtex Style

@conference{icpram16,
author={Fares Al-Qunaieer and Mohamed Alkanhal},
title={Learning from Partially Occluded Faces},
booktitle={Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2016},
pages={534-539},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005665605340539},
isbn={978-989-758-173-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Learning from Partially Occluded Faces
SN - 978-989-758-173-1
AU - Al-Qunaieer F.
AU - Alkanhal M.
PY - 2016
SP - 534
EP - 539
DO - 10.5220/0005665605340539