EUVIMEDEUVIMED entdecken
Crossref

A comparison study to detect seam carving forgery in JPEG images with deep learning models

Naciye Hafsa Celebi, Tze-Li Hsu, Qingzhong Liu

Journal of Surveillance, Security and Safety · 2022

DOI: 10.20517/jsss.2022.02 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Surveillance, Security and Safety, 2022. Verfasst von Naciye Hafsa Celebi und 2 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aim

Although deep learning has been applied in image forgery detection, to our knowledge, it still falls short of a comprehensive comparison study in detecting seam-carving images in multimedia forensics by comparing the popular deep learning models, which is addressed in this study.

Methods

To investigate the performance in detecting seam-carving-based image forgery with popular deep learning models that were used in image forensics, we compared nine different deep learning models in detecting untouched JPEG images, seam-insertion images, and seam removal images (three-class classification), and in distinguishing modified seam-carving images from untouched JPEG images (binary classification). We also investigate the different learning algorithms with the Efficientnet-B5 in adjusting the learning rate with three popular optimizers in deep learning.

Results

Our study shows that EfficientNet performs the best among the nine different deep learning frameworks, followed by SRnet, and LFnet. Different algorithms for adjusting the learning rate result in different detection testing accuracy with Efficientnet-B5. In our experiments, decouples the optimal choice of weight decay factor from the setting of the learning rate (AdamW) is generally superior to Adaptive Moment Estimation (Adam) and Stochastic Gradient Descent (SGD). Our study also indicates that deep learning is very promising for image forensics, such as the detection of image forgery.

Conclusion

Deep learning is very promising in image forensics that is hardly discernable to human perceptions, but the performance varies over different learning models and frameworks. In addition to the models, the optimizer has a considerable impact on the final detection performance. We would recommend EfficientNet, LFnet and SRnet for seam-carving detection.

Zitieren

APA

Celebi, N. H., Hsu, T., & Liu, Q. (2022). A comparison study to detect seam carving forgery in JPEG images with deep learning models. Journal of Surveillance, Security and Safety. https://doi.org/10.20517/jsss.2022.02

Vancouver

Celebi NH, Hsu T, Liu Q. A comparison study to detect seam carving forgery in JPEG images with deep learning models. Journal of Surveillance, Security and Safety. 2022. doi:10.20517/jsss.2022.02

BibTeX
@article{Celebi2022,
  author = {Celebi, Naciye Hafsa and Hsu, Tze-Li and Liu, Qingzhong},
  title = {A comparison study to detect seam carving forgery in JPEG images with deep learning models},
  journal = {Journal of Surveillance, Security and Safety},
  year = {2022},
  doi = {10.20517/jsss.2022.02}
}
Kostenlos starten →