Recovery-Based Occluded Face Recognition by Identity-Guided Inpainting
Occlusion in facial photos poses a significant challenge for machine detection and recognition. Consequently, occluded face recognition for camera-captured images has emerged as a prominent and widely discussed topic in computer vision. The present standard face recognition methods have achieved rem...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-01-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/24/2/394 |
_version_ | 1797339447308582912 |
---|---|
author | Honglei Li Yifan Zhang Wenmin Wang Shenyong Zhang Shixiong Zhang |
author_facet | Honglei Li Yifan Zhang Wenmin Wang Shenyong Zhang Shixiong Zhang |
author_sort | Honglei Li |
collection | DOAJ |
description | Occlusion in facial photos poses a significant challenge for machine detection and recognition. Consequently, occluded face recognition for camera-captured images has emerged as a prominent and widely discussed topic in computer vision. The present standard face recognition methods have achieved remarkable performance in unoccluded face recognition but performed poorly when directly applied to occluded face datasets. The main reason lies in the absence of identity cues caused by occlusions. Therefore, a direct idea of recovering the occluded areas through an inpainting model has been proposed. However, existing inpainting models based on an encoder-decoder structure are limited in preserving inherent identity information. To solve the problem, we propose ID-Inpainter, an identity-guided face inpainting model, which preserves the identity information to the greatest extent through a more accurate identity sampling strategy and a GAN-like fusing network. We conduct recognition experiments on the occluded face photographs from the LFW, CFP-FP, and AgeDB-30 datasets, and the results indicate that our method achieves state-of-the-art performance in identity-preserving inpainting, and dramatically improves the accuracy of normal recognizers in occluded face recognition. |
first_indexed | 2024-03-08T09:48:16Z |
format | Article |
id | doaj.art-eb23cac2118e43eb881391e48e3647a5 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-08T09:48:16Z |
publishDate | 2024-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-eb23cac2118e43eb881391e48e3647a52024-01-29T14:14:12ZengMDPI AGSensors1424-82202024-01-0124239410.3390/s24020394Recovery-Based Occluded Face Recognition by Identity-Guided InpaintingHonglei Li0Yifan Zhang1Wenmin Wang2Shenyong Zhang3Shixiong Zhang4School of Computer Science and Engineering, Macau University of Science and Technology, Macau, ChinaSchool of Computer Science and Engineering, Macau University of Science and Technology, Macau, ChinaSchool of Computer Science and Engineering, Macau University of Science and Technology, Macau, ChinaSchool of Computer Science and Engineering, Macau University of Science and Technology, Macau, ChinaSchool of Computer Science and Engineering, Macau University of Science and Technology, Macau, ChinaOcclusion in facial photos poses a significant challenge for machine detection and recognition. Consequently, occluded face recognition for camera-captured images has emerged as a prominent and widely discussed topic in computer vision. The present standard face recognition methods have achieved remarkable performance in unoccluded face recognition but performed poorly when directly applied to occluded face datasets. The main reason lies in the absence of identity cues caused by occlusions. Therefore, a direct idea of recovering the occluded areas through an inpainting model has been proposed. However, existing inpainting models based on an encoder-decoder structure are limited in preserving inherent identity information. To solve the problem, we propose ID-Inpainter, an identity-guided face inpainting model, which preserves the identity information to the greatest extent through a more accurate identity sampling strategy and a GAN-like fusing network. We conduct recognition experiments on the occluded face photographs from the LFW, CFP-FP, and AgeDB-30 datasets, and the results indicate that our method achieves state-of-the-art performance in identity-preserving inpainting, and dramatically improves the accuracy of normal recognizers in occluded face recognition.https://www.mdpi.com/1424-8220/24/2/394occluded face recognitionidentity-guided inpaintingimage synthesisgenerative adversarial net (GAN) |
spellingShingle | Honglei Li Yifan Zhang Wenmin Wang Shenyong Zhang Shixiong Zhang Recovery-Based Occluded Face Recognition by Identity-Guided Inpainting Sensors occluded face recognition identity-guided inpainting image synthesis generative adversarial net (GAN) |
title | Recovery-Based Occluded Face Recognition by Identity-Guided Inpainting |
title_full | Recovery-Based Occluded Face Recognition by Identity-Guided Inpainting |
title_fullStr | Recovery-Based Occluded Face Recognition by Identity-Guided Inpainting |
title_full_unstemmed | Recovery-Based Occluded Face Recognition by Identity-Guided Inpainting |
title_short | Recovery-Based Occluded Face Recognition by Identity-Guided Inpainting |
title_sort | recovery based occluded face recognition by identity guided inpainting |
topic | occluded face recognition identity-guided inpainting image synthesis generative adversarial net (GAN) |
url | https://www.mdpi.com/1424-8220/24/2/394 |
work_keys_str_mv | AT hongleili recoverybasedoccludedfacerecognitionbyidentityguidedinpainting AT yifanzhang recoverybasedoccludedfacerecognitionbyidentityguidedinpainting AT wenminwang recoverybasedoccludedfacerecognitionbyidentityguidedinpainting AT shenyongzhang recoverybasedoccludedfacerecognitionbyidentityguidedinpainting AT shixiongzhang recoverybasedoccludedfacerecognitionbyidentityguidedinpainting |