Protecting visual data privacy in offshore industry via underwater image inpainting.

Tolie, Hamidreza Farhadi; Ren, Jinchang; Chen, Rongjun; Zhao, Huimin

Abstract

Leveraging advanced artificial intelligence (AI) methodologies offers the advantage of incorporating multiple expert viewpoints, thereby facilitating a more comprehensive inspection of underwater infrastructure. However, the implementation of AI techniques in subsea tasks is hindered by the lack of extensive and diverse datasets required for effective training and inference of the AI models, emphasizing the vital need for enhanced data sharing practices within the offshore sector. The sensitive textual information within underwater survey data, such as site geolocations, water depths, mission-specific details, timestamps, and third-party data, necessitate a balanced approach to data privacy. To address this, we propose the integration of cutting-edge text detection and image inpainting techniques. These methodologies enable the identification and subsequent removal of textual regions from images while preserving the quality and natural appearance of the images. Experimental results validate the efficacy of our proposed approach in simultaneously preserving the visual quality and protecting the privacy. The removal of detected textual regions from images demonstrates less distortions, underscoring the potential of this methodology for application in offshore industry settings. This study contributes to the ongoing discourse regarding data privacy in underwater surveys, offering a viable solution to balance information sharing with confidentiality concerns.

Citation

TOLIE, H.F., REN, J., CHEN, R. and ZHAO, H. 2024. Protecting visual data privacy in offshore industry via underwater image inpainting. In Proceedings of the 9th International conference on image, vision and computing 2024 (ICIVC 2024), 15-17 July 2024, Suzhou, China. Piscataway: IEEE [online], pages 281-286. Available from: https://doi.org/10.1109/ICIVC61627.2024.10837433

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 9th International conference on image, vision and computing 2024 (ICIVC 2024)
• Start Date: Jul 15, 2024
• End Date: Jul 17, 2024
• Acceptance Date: Jun 5, 2024
• Online Publication Date: Jan 20, 2025
• Publication Date: Dec 31, 2024
• Deposit Date: Jan 28, 2025
• Publicly Available Date: Jan 28, 2025
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• Pages: 281-286
• DOI: https://doi.org/10.1109/ICIVC61627.2024.10837433
• Keywords: Underwater image; Underwater data privacy; Text detection; Image inpainting
• Public URL: https://rgu-repository.worktribe.com/output/2675131