Proposal / Submission Type
Peer Reviewed Paper
Abstract
The increasing availability of smartphones allowed people to easily capture and share images on the internet. These images are often associated with metadata, including the image capture time (timestamp) and the location where the image was captured (geolocation). The metadata associated with images provides valuable information to better understand scenes and events presented in these images. The timestamp can be manipulated intentionally to provide false information to convey a twisted version of reality. Images with manipulated timestamps are often used as a cover-up for wrongdoing or broadcasting false claims and competing views on the internet. Estimating the time of capture of a photograph is a challenging task that requires a comprehensive understanding of the scene and its geographical location. In this paper, we propose a learning-based approach based on deep learning to estimate when an outdoor image was captured. We provide a detailed quantitative and qualitative evaluation of the trained models for various settings and show that the proposed approach outperforms baseline methods.
Scholarly Commons Citation
Salem, Tawfiq; Hwang, Jisoo; and Padilha, Rafael, "Timestamp Estimation From Outdoor Scenes" (2022). Annual ADFSL Conference on Digital Forensics, Security and Law. 2.
https://commons.erau.edu/adfsl/2022/presentations/2
Included in
Aviation Safety and Security Commons, Computer Law Commons, Defense and Security Studies Commons, Forensic Science and Technology Commons, Information Security Commons, National Security Law Commons, OS and Networks Commons, Other Computer Sciences Commons, Social Control, Law, Crime, and Deviance Commons
Timestamp Estimation From Outdoor Scenes
The increasing availability of smartphones allowed people to easily capture and share images on the internet. These images are often associated with metadata, including the image capture time (timestamp) and the location where the image was captured (geolocation). The metadata associated with images provides valuable information to better understand scenes and events presented in these images. The timestamp can be manipulated intentionally to provide false information to convey a twisted version of reality. Images with manipulated timestamps are often used as a cover-up for wrongdoing or broadcasting false claims and competing views on the internet. Estimating the time of capture of a photograph is a challenging task that requires a comprehensive understanding of the scene and its geographical location. In this paper, we propose a learning-based approach based on deep learning to estimate when an outdoor image was captured. We provide a detailed quantitative and qualitative evaluation of the trained models for various settings and show that the proposed approach outperforms baseline methods.
