Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.17170 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911966132436992 |
|---|---|
| author | Mehta, Preeti Sagar, Aman Kumari, Suchi |
| author_facet | Mehta, Preeti Sagar, Aman Kumari, Suchi |
| contents | An increasing number of classification approaches have been developed to address the issue of image rebroadcast and recapturing, a standard attack strategy in insurance frauds, face spoofing, and video piracy. However, most of them neglected scale variations and domain generalization scenarios, performing poorly in instances involving domain shifts, typically made worse by inter-domain and cross-domain scale variances. To overcome these issues, we propose a cascaded data augmentation and SWIN transformer domain generalization framework (DAST-DG) in the current research work Initially, we examine the disparity in dataset representation. A feature generator is trained to make authentic images from various domains indistinguishable. This process is then applied to recaptured images, creating a dual adversarial learning setup. Extensive experiments demonstrate that our approach is practical and surpasses state-of-the-art methods across different databases. Our model achieves an accuracy of approximately 82\% with a precision of 95\% on high-variance datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_17170 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Domain Generalized Recaptured Screen Image Identification Using SWIN Transformer Mehta, Preeti Sagar, Aman Kumari, Suchi Computer Vision and Pattern Recognition An increasing number of classification approaches have been developed to address the issue of image rebroadcast and recapturing, a standard attack strategy in insurance frauds, face spoofing, and video piracy. However, most of them neglected scale variations and domain generalization scenarios, performing poorly in instances involving domain shifts, typically made worse by inter-domain and cross-domain scale variances. To overcome these issues, we propose a cascaded data augmentation and SWIN transformer domain generalization framework (DAST-DG) in the current research work Initially, we examine the disparity in dataset representation. A feature generator is trained to make authentic images from various domains indistinguishable. This process is then applied to recaptured images, creating a dual adversarial learning setup. Extensive experiments demonstrate that our approach is practical and surpasses state-of-the-art methods across different databases. Our model achieves an accuracy of approximately 82\% with a precision of 95\% on high-variance datasets. |
| title | Domain Generalized Recaptured Screen Image Identification Using SWIN Transformer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.17170 |