Learning Discriminant Spatial Features With Deep Graph-Based Convolutions for Occluded Face Detection
The use of face masks has become a widespread non-pharmaceutical practice to mitigate the transmission of COVID-19. However, achieving accurate facial detection while people wear masks or similar face occlusions is a major challenge. This paper introduces a model to detect occluded or masked faces b...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9745090/ |
| _version_ | 1819047447499898880 |
|---|---|
| author | Firas Albalas Ahmad Alzu'bi Alanoud Alguzo Tawfik Al-Hadhrami Achraf Othman |
| author_facet | Firas Albalas Ahmad Alzu'bi Alanoud Alguzo Tawfik Al-Hadhrami Achraf Othman |
| author_sort | Firas Albalas |
| collection | DOAJ |
| description | The use of face masks has become a widespread non-pharmaceutical practice to mitigate the transmission of COVID-19. However, achieving accurate facial detection while people wear masks or similar face occlusions is a major challenge. This paper introduces a model to detect occluded or masked faces based on fused convolutional graphs. This model includes a deep neural architecture with two spatial-based graphs that rely on a set of key facial features. First, a distance graph is used to identify geographical similarity between the facial nodes that represent certain key face parts. Second, a correlation graph is formulated to compute the correlations between every two nodes that represent two different augmented facial modalities. Transfer learning is then performed using a pretrained deep architecture as a baseline to map the abstract semantic information into multiple feature filters. Then, discriminant graph convolutions are constructed based on the fusion of distance and correlation graphs. This model evaluates two tasks of facial detection, which are the binary detection of masked or unmasked faces, and multi-category detection of masked, unmasked, or occluded face with no mask. The experimental results on two benchmarking real-world datasets show that the proposed deep learning model is highly effective with an accuracy of 98% achieved in binary detection. Even with high variance in image occlusions, our proposed model has great promise in detecting and distinguishing between types of facial occlusion with an accuracy of 86% reported in multi-category detection. |
| first_indexed | 2024-12-21T11:00:30Z |
| format | Article |
| id | doaj.art-c912e30113d646bbbad3c9a88229f682 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-21T11:00:30Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-c912e30113d646bbbad3c9a88229f6822022-12-21T19:06:22ZengIEEEIEEE Access2169-35362022-01-0110351623517110.1109/ACCESS.2022.31635659745090Learning Discriminant Spatial Features With Deep Graph-Based Convolutions for Occluded Face DetectionFiras Albalas0https://orcid.org/0000-0002-3060-9998Ahmad Alzu'bi1https://orcid.org/0000-0001-5466-0379Alanoud Alguzo2Tawfik Al-Hadhrami3https://orcid.org/0000-0001-7441-604XAchraf Othman4https://orcid.org/0000-0003-1290-2098Department of Computer Science, Jordan University of Science and Technology, Irbid, JordanDepartment of Computer Science, Jordan University of Science and Technology, Irbid, JordanDepartment of Computer Science, Jordan University of Science and Technology, Irbid, JordanSchool of Science and Technology, Nottingham Trent University, Nottingham, U.KMada Center, Doha, QatarThe use of face masks has become a widespread non-pharmaceutical practice to mitigate the transmission of COVID-19. However, achieving accurate facial detection while people wear masks or similar face occlusions is a major challenge. This paper introduces a model to detect occluded or masked faces based on fused convolutional graphs. This model includes a deep neural architecture with two spatial-based graphs that rely on a set of key facial features. First, a distance graph is used to identify geographical similarity between the facial nodes that represent certain key face parts. Second, a correlation graph is formulated to compute the correlations between every two nodes that represent two different augmented facial modalities. Transfer learning is then performed using a pretrained deep architecture as a baseline to map the abstract semantic information into multiple feature filters. Then, discriminant graph convolutions are constructed based on the fusion of distance and correlation graphs. This model evaluates two tasks of facial detection, which are the binary detection of masked or unmasked faces, and multi-category detection of masked, unmasked, or occluded face with no mask. The experimental results on two benchmarking real-world datasets show that the proposed deep learning model is highly effective with an accuracy of 98% achieved in binary detection. Even with high variance in image occlusions, our proposed model has great promise in detecting and distinguishing between types of facial occlusion with an accuracy of 86% reported in multi-category detection.https://ieeexplore.ieee.org/document/9745090/Correlation graphsdeep learningdistance graphgraph convolutional networksface maskoccluded face detection |
| spellingShingle | Firas Albalas Ahmad Alzu'bi Alanoud Alguzo Tawfik Al-Hadhrami Achraf Othman Learning Discriminant Spatial Features With Deep Graph-Based Convolutions for Occluded Face Detection IEEE Access Correlation graphs deep learning distance graph graph convolutional networks face mask occluded face detection |
| title | Learning Discriminant Spatial Features With Deep Graph-Based Convolutions for Occluded Face Detection |
| title_full | Learning Discriminant Spatial Features With Deep Graph-Based Convolutions for Occluded Face Detection |
| title_fullStr | Learning Discriminant Spatial Features With Deep Graph-Based Convolutions for Occluded Face Detection |
| title_full_unstemmed | Learning Discriminant Spatial Features With Deep Graph-Based Convolutions for Occluded Face Detection |
| title_short | Learning Discriminant Spatial Features With Deep Graph-Based Convolutions for Occluded Face Detection |
| title_sort | learning discriminant spatial features with deep graph based convolutions for occluded face detection |
| topic | Correlation graphs deep learning distance graph graph convolutional networks face mask occluded face detection |
| url | https://ieeexplore.ieee.org/document/9745090/ |
| work_keys_str_mv | AT firasalbalas learningdiscriminantspatialfeatureswithdeepgraphbasedconvolutionsforoccludedfacedetection AT ahmadalzubi learningdiscriminantspatialfeatureswithdeepgraphbasedconvolutionsforoccludedfacedetection AT alanoudalguzo learningdiscriminantspatialfeatureswithdeepgraphbasedconvolutionsforoccludedfacedetection AT tawfikalhadhrami learningdiscriminantspatialfeatureswithdeepgraphbasedconvolutionsforoccludedfacedetection AT achrafothman learningdiscriminantspatialfeatureswithdeepgraphbasedconvolutionsforoccludedfacedetection |