Face Recognition Method for Underground Engineering Based on Dual-Target Domain Adaptation and Discriminative Feature Learning
The poor lighting and dust in underground engineering environments often induce serious noise and motion blur to face recognition cameras, decreasing the recognition accuracy even under Near-InfraRed (NIR) mode. Although various methods to improve algorithm robustness can enhance the overall model p...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10840193/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823859646714085376 |
|---|---|
| author | Yongqiang Yu Cong Guo Lidan Fan Jiyun Zhang Liwei Yu Peitao Li |
| author_facet | Yongqiang Yu Cong Guo Lidan Fan Jiyun Zhang Liwei Yu Peitao Li |
| author_sort | Yongqiang Yu |
| collection | DOAJ |
| description | The poor lighting and dust in underground engineering environments often induce serious noise and motion blur to face recognition cameras, decreasing the recognition accuracy even under Near-InfraRed (NIR) mode. Although various methods to improve algorithm robustness can enhance the overall model performance, the face recognition accuracy remains insufficient for the large number of blurred and NIR images generated during underground engineering. Accordingly, this paper proposes a novel face recognition method for underground engineering environments based on dual-target domain adaptation (DTDA) and discriminative feature learning (DFL). The targeting of the algorithm to blurred and NIR images is enhanced through DTDA, while the inter-class feature variability and intra-class feature compactness for domain adaptation face recognition are ensured by DFL. Extensive experiments are conducted on public and self-built datasets to verify the proposed method. The results show that <xref ref-type="disp-formula" rid="deqn1">(1)</xref> dual domain adversarial loss, dual CORAL loss, Blur-to-Sharp and NIR-to-VIS image reconstruction, and face keypoints intermediate domain can improve the DTDA performance of the model. <xref ref-type="disp-formula" rid="deqn2">(2)</xref> Dedicated encoders, center loss, and triplet loss can improve the DFL ability of the model. <xref ref-type="disp-formula" rid="deqn3-deqn5">(3)</xref> The high Rank-1 accuracies and area under curve (AUC) values of the Receiver Operating Characteristic (ROC) curves on the three domains indicate that the proposed face recognition method can adapt to the complex working conditions in underground engineering environments. |
| format | Article |
| id | doaj-art-d28d7e1abd464ab49ca82f662ff5e981 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-d28d7e1abd464ab49ca82f662ff5e9812025-02-11T00:01:34ZengIEEEIEEE Access2169-35362025-01-0113242232423610.1109/ACCESS.2025.352969810840193Face Recognition Method for Underground Engineering Based on Dual-Target Domain Adaptation and Discriminative Feature LearningYongqiang Yu0Cong Guo1https://orcid.org/0009-0009-6473-9764Lidan Fan2Jiyun Zhang3Liwei Yu4Peitao Li5School of Civil Engineering, Henan Polytechnic University, Jiaozuo, ChinaSchool of Civil Engineering, Henan Polytechnic University, Jiaozuo, ChinaSchool of Civil Engineering, Henan Polytechnic University, Jiaozuo, ChinaSchool of Civil Engineering, Henan Polytechnic University, Jiaozuo, ChinaHenan Railway Construction and Investment Group Company Ltd., Zhengzhou, ChinaSchool of Civil Engineering, Henan Polytechnic University, Jiaozuo, ChinaThe poor lighting and dust in underground engineering environments often induce serious noise and motion blur to face recognition cameras, decreasing the recognition accuracy even under Near-InfraRed (NIR) mode. Although various methods to improve algorithm robustness can enhance the overall model performance, the face recognition accuracy remains insufficient for the large number of blurred and NIR images generated during underground engineering. Accordingly, this paper proposes a novel face recognition method for underground engineering environments based on dual-target domain adaptation (DTDA) and discriminative feature learning (DFL). The targeting of the algorithm to blurred and NIR images is enhanced through DTDA, while the inter-class feature variability and intra-class feature compactness for domain adaptation face recognition are ensured by DFL. Extensive experiments are conducted on public and self-built datasets to verify the proposed method. The results show that <xref ref-type="disp-formula" rid="deqn1">(1)</xref> dual domain adversarial loss, dual CORAL loss, Blur-to-Sharp and NIR-to-VIS image reconstruction, and face keypoints intermediate domain can improve the DTDA performance of the model. <xref ref-type="disp-formula" rid="deqn2">(2)</xref> Dedicated encoders, center loss, and triplet loss can improve the DFL ability of the model. <xref ref-type="disp-formula" rid="deqn3-deqn5">(3)</xref> The high Rank-1 accuracies and area under curve (AUC) values of the Receiver Operating Characteristic (ROC) curves on the three domains indicate that the proposed face recognition method can adapt to the complex working conditions in underground engineering environments.https://ieeexplore.ieee.org/document/10840193/Dual-target domain adaptationdiscriminative feature learningface recognitionunderground engineering |
| spellingShingle | Yongqiang Yu Cong Guo Lidan Fan Jiyun Zhang Liwei Yu Peitao Li Face Recognition Method for Underground Engineering Based on Dual-Target Domain Adaptation and Discriminative Feature Learning IEEE Access Dual-target domain adaptation discriminative feature learning face recognition underground engineering |
| title | Face Recognition Method for Underground Engineering Based on Dual-Target Domain Adaptation and Discriminative Feature Learning |
| title_full | Face Recognition Method for Underground Engineering Based on Dual-Target Domain Adaptation and Discriminative Feature Learning |
| title_fullStr | Face Recognition Method for Underground Engineering Based on Dual-Target Domain Adaptation and Discriminative Feature Learning |
| title_full_unstemmed | Face Recognition Method for Underground Engineering Based on Dual-Target Domain Adaptation and Discriminative Feature Learning |
| title_short | Face Recognition Method for Underground Engineering Based on Dual-Target Domain Adaptation and Discriminative Feature Learning |
| title_sort | face recognition method for underground engineering based on dual target domain adaptation and discriminative feature learning |
| topic | Dual-target domain adaptation discriminative feature learning face recognition underground engineering |
| url | https://ieeexplore.ieee.org/document/10840193/ |
| work_keys_str_mv | AT yongqiangyu facerecognitionmethodforundergroundengineeringbasedondualtargetdomainadaptationanddiscriminativefeaturelearning AT congguo facerecognitionmethodforundergroundengineeringbasedondualtargetdomainadaptationanddiscriminativefeaturelearning AT lidanfan facerecognitionmethodforundergroundengineeringbasedondualtargetdomainadaptationanddiscriminativefeaturelearning AT jiyunzhang facerecognitionmethodforundergroundengineeringbasedondualtargetdomainadaptationanddiscriminativefeaturelearning AT liweiyu facerecognitionmethodforundergroundengineeringbasedondualtargetdomainadaptationanddiscriminativefeaturelearning AT peitaoli facerecognitionmethodforundergroundengineeringbasedondualtargetdomainadaptationanddiscriminativefeaturelearning |