Investigating Atrous Rate Reduction in DeepLabV3+ for Improved Image Tampering Localization: A New Module and Dataset Approach
3
Issued Date
2025-01-01
Resource Type
eISSN
18826652
Scopus ID
2-s2.0-105003407228
Journal Title
Journal of Information Processing
Volume
33
Start Page
264
End Page
275
Rights Holder(s)
SCOPUS
Bibliographic Citation
Journal of Information Processing Vol.33 (2025) , 264-275
Suggested Citation
Rao J., Teerakanok S., Uehara T. Investigating Atrous Rate Reduction in DeepLabV3+ for Improved Image Tampering Localization: A New Module and Dataset Approach. Journal of Information Processing Vol.33 (2025) , 264-275. 275. doi:10.2197/ipsjjip.33.264 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/109910
Title
Investigating Atrous Rate Reduction in DeepLabV3+ for Improved Image Tampering Localization: A New Module and Dataset Approach
Author(s)
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
With the popularity of digital images in communications and media, image tampering detection has be-come an important research topic in the field of computer vision. This study uses the DeepLabV3+ model to explore the impact of dilated convolution rate changes and attention mechanisms on the accuracy of image tampering location and particularly emphasizes the application of independently created mobile image tampering datasets in experiments. First, we verified the effectiveness of DeepLabV3+ on basic image segmentation tasks and tried to apply it to more complex image tampering detection tasks. Through a series of experiments, we found that reducing the atrous convolution rate can reduce model complexity and improve training efficiency without significantly affecting accuracy. Furthermore, we integrate channel attention and spatial attention mechanisms, aiming to enhance the model’s recognition accuracy of tampered areas. In particular, the mobile datasets we developed contain images shot with smartphones and then tampered with using the phone’s built-in editing tools. These datasets play a key role in validating the model’s ability to handle real-world tampering scenarios.