Home > Research > Publications & Outputs > Multi-descriptor random sampling for patch-base...

Links

Text available via DOI:

View graph of relations

Multi-descriptor random sampling for patch-based face recognition

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Multi-descriptor random sampling for patch-based face recognition. / Cheheb, I.; Al-Maadeed, N.; Bouridane, A. et al.
In: Applied Sciences, Vol. 11, No. 14, 6603, 08.07.2021.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Cheheb, I, Al-Maadeed, N, Bouridane, A, Beghdadi, A & Jiang, R 2021, 'Multi-descriptor random sampling for patch-based face recognition', Applied Sciences, vol. 11, no. 14, 6603. https://doi.org/10.3390/app11146303

APA

Cheheb, I., Al-Maadeed, N., Bouridane, A., Beghdadi, A., & Jiang, R. (2021). Multi-descriptor random sampling for patch-based face recognition. Applied Sciences, 11(14), Article 6603. https://doi.org/10.3390/app11146303

Vancouver

Cheheb I, Al-Maadeed N, Bouridane A, Beghdadi A, Jiang R. Multi-descriptor random sampling for patch-based face recognition. Applied Sciences. 2021 Jul 8;11(14):6603. doi: 10.3390/app11146303

Author

Cheheb, I. ; Al-Maadeed, N. ; Bouridane, A. et al. / Multi-descriptor random sampling for patch-based face recognition. In: Applied Sciences. 2021 ; Vol. 11, No. 14.

Bibtex

@article{7f5f5f2b1f91420ab2255ab7ea5a9314,
title = "Multi-descriptor random sampling for patch-based face recognition",
abstract = "While there has been a massive increase in research into face recognition, it remains a challenging problem due to conditions present in real life. This paper focuses on the inherently present issue of partial occlusion distortions in real face recognition applications. We propose an approach to tackle this problem. First, face images are divided into multiple patches before local descriptors of Local Binary Patterns and Histograms of Oriented Gradients are applied on each patch. Next, the resulting histograms are concatenated, and their dimensionality is then reduced using Kernel Principle Component Analysis. Once completed, patches are randomly selected using the concept of random sampling to finally construct several sub-Support Vector Machine classifiers. The results obtained from these sub-classifiers are combined to generate the final recognition outcome. Experimental results based on the AR face database and the Extended Yale B database show the effectiveness of our proposed technique. ",
keywords = "Face recognition, Random sampling, SVM classification",
author = "I. Cheheb and N. Al-Maadeed and A. Bouridane and A. Beghdadi and R. Jiang",
year = "2021",
month = jul,
day = "8",
doi = "10.3390/app11146303",
language = "English",
volume = "11",
journal = "Applied Sciences",
issn = "2076-3417",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "14",

}

RIS

TY - JOUR

T1 - Multi-descriptor random sampling for patch-based face recognition

AU - Cheheb, I.

AU - Al-Maadeed, N.

AU - Bouridane, A.

AU - Beghdadi, A.

AU - Jiang, R.

PY - 2021/7/8

Y1 - 2021/7/8

N2 - While there has been a massive increase in research into face recognition, it remains a challenging problem due to conditions present in real life. This paper focuses on the inherently present issue of partial occlusion distortions in real face recognition applications. We propose an approach to tackle this problem. First, face images are divided into multiple patches before local descriptors of Local Binary Patterns and Histograms of Oriented Gradients are applied on each patch. Next, the resulting histograms are concatenated, and their dimensionality is then reduced using Kernel Principle Component Analysis. Once completed, patches are randomly selected using the concept of random sampling to finally construct several sub-Support Vector Machine classifiers. The results obtained from these sub-classifiers are combined to generate the final recognition outcome. Experimental results based on the AR face database and the Extended Yale B database show the effectiveness of our proposed technique.

AB - While there has been a massive increase in research into face recognition, it remains a challenging problem due to conditions present in real life. This paper focuses on the inherently present issue of partial occlusion distortions in real face recognition applications. We propose an approach to tackle this problem. First, face images are divided into multiple patches before local descriptors of Local Binary Patterns and Histograms of Oriented Gradients are applied on each patch. Next, the resulting histograms are concatenated, and their dimensionality is then reduced using Kernel Principle Component Analysis. Once completed, patches are randomly selected using the concept of random sampling to finally construct several sub-Support Vector Machine classifiers. The results obtained from these sub-classifiers are combined to generate the final recognition outcome. Experimental results based on the AR face database and the Extended Yale B database show the effectiveness of our proposed technique.

KW - Face recognition

KW - Random sampling

KW - SVM classification

U2 - 10.3390/app11146303

DO - 10.3390/app11146303

M3 - Journal article

VL - 11

JO - Applied Sciences

JF - Applied Sciences

SN - 2076-3417

IS - 14

M1 - 6603

ER -