Content-aware generation of copy-move text forgeries
A copy-move image forgery generally refers to copying a portion of an image and re-inserting it elsewhere in the same image, with the intent of hiding undesirable contents or duplicating particular objects of interest. In particular, this thesis deals with copy-move tampering in scanned versions of printed text documents.
The goal of the thesis is to extend an available toolbox with the content-aware creation of copy-move forgeries of scanned text images and enable the automatic generation of semantically meaningful text forgeries.
Student's interest (first experience) in image processing and/or OCR
- Christlein, V., Riess, C., Jordan, J., Riess, C., and Angelopoulou, E. An Evaluation of Popular Copy–Move Forgery Detection Approaches. IEEE Transactions on Information Forensics and Security, 7, 6 (2012), 1841–1854.
- Abramova, S. and Böhme, R. Detecting Copy–Move Forgeries in Scanned Text Documents. In Proceedings of IS&T Electronic Imaging: Media Watermarking, Security, and Forensics 2016. San Francisco, CA, 2016. [PDF]