Face Anti-Spoofing Based on Adaptive Channel Enhancement and Intra-Class Constraint
Face anti-spoofing detection is crucial for identity verification and security monitoring. However, existing single-modal models struggle with feature extraction under complex lighting conditions and background variations. Moreover, the feature distributions of live and spoofed samples often overlap...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/11/4/116 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849714114626060288 |
|---|---|
| author | Ye Li Wenzhe Sun Zuhe Li Xiang Guo |
| author_facet | Ye Li Wenzhe Sun Zuhe Li Xiang Guo |
| author_sort | Ye Li |
| collection | DOAJ |
| description | Face anti-spoofing detection is crucial for identity verification and security monitoring. However, existing single-modal models struggle with feature extraction under complex lighting conditions and background variations. Moreover, the feature distributions of live and spoofed samples often overlap, resulting in suboptimal classification performance. To address these issues, we propose a jointly optimized framework integrating the Enhanced Channel Attention (ECA) mechanism and the Intra-Class Differentiator (ICD). The ECA module extracts features through deep convolution, while the Bottleneck Reconstruction Module (BRM) employs a channel compression–expansion mechanism to refine spatial feature selection. Furthermore, the channel attention mechanism enhances key channel representation. Meanwhile, the ICD mechanism enforces intra-class compactness and inter-class separability, optimizing feature distribution both within and across classes, thereby improving feature learning and generalization performance. Experimental results show that our framework achieves average classification error rates (ACERs) of 2.45%, 1.16%, 1.74%, and 2.17% on the CASIA-SURF, CASIA-SURF CeFA, CASIA-FASD, and OULU-NPU datasets, outperforming existing methods. |
| format | Article |
| id | doaj-art-91c433e98fa74cef9888d83e0f2f44d7 |
| institution | DOAJ |
| issn | 2313-433X |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj-art-91c433e98fa74cef9888d83e0f2f44d72025-08-20T03:13:47ZengMDPI AGJournal of Imaging2313-433X2025-04-0111411610.3390/jimaging11040116Face Anti-Spoofing Based on Adaptive Channel Enhancement and Intra-Class ConstraintYe Li0Wenzhe Sun1Zuhe Li2Xiang Guo3School of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaSchool of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaSchool of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaSchool of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaFace anti-spoofing detection is crucial for identity verification and security monitoring. However, existing single-modal models struggle with feature extraction under complex lighting conditions and background variations. Moreover, the feature distributions of live and spoofed samples often overlap, resulting in suboptimal classification performance. To address these issues, we propose a jointly optimized framework integrating the Enhanced Channel Attention (ECA) mechanism and the Intra-Class Differentiator (ICD). The ECA module extracts features through deep convolution, while the Bottleneck Reconstruction Module (BRM) employs a channel compression–expansion mechanism to refine spatial feature selection. Furthermore, the channel attention mechanism enhances key channel representation. Meanwhile, the ICD mechanism enforces intra-class compactness and inter-class separability, optimizing feature distribution both within and across classes, thereby improving feature learning and generalization performance. Experimental results show that our framework achieves average classification error rates (ACERs) of 2.45%, 1.16%, 1.74%, and 2.17% on the CASIA-SURF, CASIA-SURF CeFA, CASIA-FASD, and OULU-NPU datasets, outperforming existing methods.https://www.mdpi.com/2313-433X/11/4/116face anti-spoofingenhanced channel attentionintra-class differentiator |
| spellingShingle | Ye Li Wenzhe Sun Zuhe Li Xiang Guo Face Anti-Spoofing Based on Adaptive Channel Enhancement and Intra-Class Constraint Journal of Imaging face anti-spoofing enhanced channel attention intra-class differentiator |
| title | Face Anti-Spoofing Based on Adaptive Channel Enhancement and Intra-Class Constraint |
| title_full | Face Anti-Spoofing Based on Adaptive Channel Enhancement and Intra-Class Constraint |
| title_fullStr | Face Anti-Spoofing Based on Adaptive Channel Enhancement and Intra-Class Constraint |
| title_full_unstemmed | Face Anti-Spoofing Based on Adaptive Channel Enhancement and Intra-Class Constraint |
| title_short | Face Anti-Spoofing Based on Adaptive Channel Enhancement and Intra-Class Constraint |
| title_sort | face anti spoofing based on adaptive channel enhancement and intra class constraint |
| topic | face anti-spoofing enhanced channel attention intra-class differentiator |
| url | https://www.mdpi.com/2313-433X/11/4/116 |
| work_keys_str_mv | AT yeli faceantispoofingbasedonadaptivechannelenhancementandintraclassconstraint AT wenzhesun faceantispoofingbasedonadaptivechannelenhancementandintraclassconstraint AT zuheli faceantispoofingbasedonadaptivechannelenhancementandintraclassconstraint AT xiangguo faceantispoofingbasedonadaptivechannelenhancementandintraclassconstraint |