Deep-learning-CNN for detecting covered faces with niqab
Detecting occluded faces is a non-trivial problem for face detection in computer vision. This challenge becomes more difficult when the occlusion covers majority of the face. Despite the high performance of current state-of-the-art face detection algorithms, the detection of occluded and covered fac...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
University of Tehran
2022
|
Subjects: | |
Online Access: | http://eprints.utm.my/103310/1/MohdShahrizalSunar2022_DeepLearningCNNforDetectingCovered.pdf |
_version_ | 1796867435942379520 |
---|---|
author | Alashbi, Abdulaziz A. Sunar, Mohd Shahrizal Alqahtani, Zieb |
author_facet | Alashbi, Abdulaziz A. Sunar, Mohd Shahrizal Alqahtani, Zieb |
author_sort | Alashbi, Abdulaziz A. |
collection | ePrints |
description | Detecting occluded faces is a non-trivial problem for face detection in computer vision. This challenge becomes more difficult when the occlusion covers majority of the face. Despite the high performance of current state-of-the-art face detection algorithms, the detection of occluded and covered faces is an unsolved problem and is still worthy of study. In this paper, a deep-learning-face-detection model Niqab-Face-Detector is proposed along with context-based labeling technique for detecting unconstrained veiled faces such as faces covered with niqab. An experimental test was conducted to evaluate the performances of the proposed model using the Niqab-Face dataset. The experiment showed encouraging results and improved accuracy compared with state-of-the-art face detection algorithms. |
first_indexed | 2024-03-05T21:27:13Z |
format | Article |
id | utm.eprints-103310 |
institution | Universiti Teknologi Malaysia - ePrints |
language | English |
last_indexed | 2024-03-05T21:27:13Z |
publishDate | 2022 |
publisher | University of Tehran |
record_format | dspace |
spelling | utm.eprints-1033102023-10-31T02:30:47Z http://eprints.utm.my/103310/ Deep-learning-CNN for detecting covered faces with niqab Alashbi, Abdulaziz A. Sunar, Mohd Shahrizal Alqahtani, Zieb QA75 Electronic computers. Computer science Detecting occluded faces is a non-trivial problem for face detection in computer vision. This challenge becomes more difficult when the occlusion covers majority of the face. Despite the high performance of current state-of-the-art face detection algorithms, the detection of occluded and covered faces is an unsolved problem and is still worthy of study. In this paper, a deep-learning-face-detection model Niqab-Face-Detector is proposed along with context-based labeling technique for detecting unconstrained veiled faces such as faces covered with niqab. An experimental test was conducted to evaluate the performances of the proposed model using the Niqab-Face dataset. The experiment showed encouraging results and improved accuracy compared with state-of-the-art face detection algorithms. University of Tehran 2022 Article PeerReviewed application/pdf en http://eprints.utm.my/103310/1/MohdShahrizalSunar2022_DeepLearningCNNforDetectingCovered.pdf Alashbi, Abdulaziz A. and Sunar, Mohd Shahrizal and Alqahtani, Zieb (2022) Deep-learning-CNN for detecting covered faces with niqab. Journal of Information Technology Management, 14 (n/a). pp. 114-123. ISSN 2008-5893 http://dx.doi.org/10.22059/JITM.2022.84888 DOI: 10.22059/JITM.2022.84888 |
spellingShingle | QA75 Electronic computers. Computer science Alashbi, Abdulaziz A. Sunar, Mohd Shahrizal Alqahtani, Zieb Deep-learning-CNN for detecting covered faces with niqab |
title | Deep-learning-CNN for detecting covered faces with niqab |
title_full | Deep-learning-CNN for detecting covered faces with niqab |
title_fullStr | Deep-learning-CNN for detecting covered faces with niqab |
title_full_unstemmed | Deep-learning-CNN for detecting covered faces with niqab |
title_short | Deep-learning-CNN for detecting covered faces with niqab |
title_sort | deep learning cnn for detecting covered faces with niqab |
topic | QA75 Electronic computers. Computer science |
url | http://eprints.utm.my/103310/1/MohdShahrizalSunar2022_DeepLearningCNNforDetectingCovered.pdf |
work_keys_str_mv | AT alashbiabdulaziza deeplearningcnnfordetectingcoveredfaceswithniqab AT sunarmohdshahrizal deeplearningcnnfordetectingcoveredfaceswithniqab AT alqahtanizieb deeplearningcnnfordetectingcoveredfaceswithniqab |