Logo

Development of a software framework for the detection of copy-move text forgeries: analysis of text 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 (content) areas of an image. It is closely related to the other thesis that concerns the analysis of text-free, background 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]