Hyperdimensional Multimedia Perception and Frontier Security

Journal article

Tong Liu, Xiaochen Yuan, Zhiyao Xie, Kaiqi Zhao, Guoheng Huang, Chi-Man Pun
IEEE Transactions on Industrial Informatics, vol. 21, 2025, pp. 1299-1308

DOI: 10.1109/TII.2024.3476541

Link

Cite

APA Click to copy
Liu, T., Yuan, X., Xie, Z., Zhao, K., Huang, G., & Pun, C.-M. (2025). A Two-Phase Scheme by Integration of Deep and Corner Feature for Balanced Copy-Move Forgery Localization. IEEE Transactions on Industrial Informatics, 21, 1299–1308. https://doi.org/10.1109/TII.2024.3476541

Chicago/Turabian Click to copy
Liu, Tong, Xiaochen Yuan, Zhiyao Xie, Kaiqi Zhao, Guoheng Huang, and Chi-Man Pun. “A Two-Phase Scheme by Integration of Deep and Corner Feature for Balanced Copy-Move Forgery Localization.” IEEE Transactions on Industrial Informatics 21 (2025): 1299–1308.

MLA Click to copy
Liu, Tong, et al. “A Two-Phase Scheme by Integration of Deep and Corner Feature for Balanced Copy-Move Forgery Localization.” IEEE Transactions on Industrial Informatics, vol. 21, 2025, pp. 1299–308, doi:10.1109/TII.2024.3476541.

BibTeX Click to copy

@article{liu2025a,
  title = {A Two-Phase Scheme by Integration of Deep and Corner Feature for Balanced Copy-Move Forgery Localization},
  year = {2025},
  journal = {IEEE Transactions on Industrial Informatics},
  pages = {1299-1308},
  volume = {21},
  doi = {10.1109/TII.2024.3476541},
  author = {Liu, Tong and Yuan, Xiaochen and Xie, Zhiyao and Zhao, Kaiqi and Huang, Guoheng and Pun, Chi-Man}
}

[Picture]

Abstract: In the era of Industry 4.0, the widespread application of digitization, automation, and Internet technology in industrial production has led to a significant increase in image data. Image security has become crucial because images are at risk of being tampered with at any time. To protect its authenticity, this article proposes a two-phase scheme to achieve balanced performance between accuracy and speed for copy-move forgery detection. Our scheme is divided into detection and localization phases. In the detection phase, the deep features are utilized to calculate the inner similarity. To improve the accuracy, a corner point matching technique is performed on the localization phase as a refinement step. The experimental results demonstrate the average F1-score is 0.6334 on CASIA2.0, making a 14.16% improvement. The computation time for each image is only 0.791 s in average. It has great significance in protecting the reliability and authenticity of industrial data.