Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture covers advanced topics in watermarking presented by the instructor, including resisting scaling and rotations, self-referenced watermarking, self-reference watermark embedding, correlation of estimated watermark, wavelet domain watermarking, robustness to compression, watermarking evaluation benchmarks, and types of attacks such as geometric transforms, JPEG compression, enhancement techniques, and more. The lecture also discusses important parameters for watermarking systems, visual quality metrics, performance evaluation, and representation through graphs like BER vs. Attack Strength, BER vs. Visual Quality, and Attack vs. Visual Quality. The presentation concludes with benchmarking techniques using a standard image database for evaluation.