Ensemble Approach for Image Recompression-Based Forgery Detection
In today’s digital age, images are vulnerable to manipulation for malicious purposes such as spreading fake news, prompting active research in image forgery detection. With the advances in deep learning (DL), convolutional neural network (CNN) and Transformer models have emerged as promin...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10811899/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849240575709020160 |
|---|---|
| author | Se-Jun Ham Van-Ha Hoang Chun-Su Park |
| author_facet | Se-Jun Ham Van-Ha Hoang Chun-Su Park |
| author_sort | Se-Jun Ham |
| collection | DOAJ |
| description | In today’s digital age, images are vulnerable to manipulation for malicious purposes such as spreading fake news, prompting active research in image forgery detection. With the advances in deep learning (DL), convolutional neural network (CNN) and Transformer models have emerged as prominent tools in this field. However, individual models may excel with certain images while performing poorly with others, leading to variability in model performance. To address this issue, this paper proposes an ensemble approach that combines predictions from multiple models to improve system performance and robustness. First, we utilize a set of pretrained DL models, including CNN-based models, Transformer-based models, and fusion models that combine these architectures, and select the best-performing models. Then, these selected models are employed in an ensemble approach using hard voting and soft voting to evaluate their collective performance. Notably, among the selected ensemble of ConvNeXt, SwinV2, and CAFormer, the hard voting technique achieves an accuracy of 97.42%, which is approximately a 6.34% improvement over the baseline model. This result confirms the effectiveness of the proposed ensemble approach for forgery detection. |
| format | Article |
| id | doaj-art-1f4e2b1c016b4a59a334d0b6ef062824 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-1f4e2b1c016b4a59a334d0b6ef0628242025-08-20T04:00:33ZengIEEEIEEE Access2169-35362024-01-011219644219645410.1109/ACCESS.2024.352129010811899Ensemble Approach for Image Recompression-Based Forgery DetectionSe-Jun Ham0Van-Ha Hoang1https://orcid.org/0000-0001-6248-4539Chun-Su Park2https://orcid.org/0000-0003-4250-2597Department of Computer Education, Sungkyunkwan University, Seoul, South KoreaDepartment of Software, Sejong University, Seoul, South KoreaDepartment of Computer Education, Sungkyunkwan University, Seoul, South KoreaIn today’s digital age, images are vulnerable to manipulation for malicious purposes such as spreading fake news, prompting active research in image forgery detection. With the advances in deep learning (DL), convolutional neural network (CNN) and Transformer models have emerged as prominent tools in this field. However, individual models may excel with certain images while performing poorly with others, leading to variability in model performance. To address this issue, this paper proposes an ensemble approach that combines predictions from multiple models to improve system performance and robustness. First, we utilize a set of pretrained DL models, including CNN-based models, Transformer-based models, and fusion models that combine these architectures, and select the best-performing models. Then, these selected models are employed in an ensemble approach using hard voting and soft voting to evaluate their collective performance. Notably, among the selected ensemble of ConvNeXt, SwinV2, and CAFormer, the hard voting technique achieves an accuracy of 97.42%, which is approximately a 6.34% improvement over the baseline model. This result confirms the effectiveness of the proposed ensemble approach for forgery detection.https://ieeexplore.ieee.org/document/10811899/Image forgery detectiondeep learningpre-trained modelsensemble techniques |
| spellingShingle | Se-Jun Ham Van-Ha Hoang Chun-Su Park Ensemble Approach for Image Recompression-Based Forgery Detection IEEE Access Image forgery detection deep learning pre-trained models ensemble techniques |
| title | Ensemble Approach for Image Recompression-Based Forgery Detection |
| title_full | Ensemble Approach for Image Recompression-Based Forgery Detection |
| title_fullStr | Ensemble Approach for Image Recompression-Based Forgery Detection |
| title_full_unstemmed | Ensemble Approach for Image Recompression-Based Forgery Detection |
| title_short | Ensemble Approach for Image Recompression-Based Forgery Detection |
| title_sort | ensemble approach for image recompression based forgery detection |
| topic | Image forgery detection deep learning pre-trained models ensemble techniques |
| url | https://ieeexplore.ieee.org/document/10811899/ |
| work_keys_str_mv | AT sejunham ensembleapproachforimagerecompressionbasedforgerydetection AT vanhahoang ensembleapproachforimagerecompressionbasedforgerydetection AT chunsupark ensembleapproachforimagerecompressionbasedforgerydetection |