Logo

Development of a software framework for the detection of copy-move text forgeries: analysis of background areas

DegreeBachelor
StatusAvailable
Supervisor(s)Svetlana Abramova, MSc

Description

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. This thesis concerns the detection of copy-move tampering operations in text documents (e.g., scans of certificates).

The objective is to implement a software framework for the detection of copy-move text forgeries following the approach in Abramova and Böhme (2016). This thesis should focus on the analysis and detection of copy-move operations in text-free, background areas of an image. It is closely related to the other thesis that concerns the analysis of text (content) areas. Both theses require an integration of Optical Character Recognition (OCR) into the processing pipeline.

Prerequisites

Student's interest (first experience) in image processing and/or OCR

References

  • 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]