Digital image forensics

• Main Author: Ng, Nou Xian.
• Other Authors: Sabu Emmanuel
• Format: Final Year Project
• Language: English
• Published: 2013
• Subjects: DRNTU::Engineering::Computer science and engineering
• Online Access: http://hdl.handle.net/10356/51883
• Institution: Nanyang Technological University

We live in an age where the use of digital photography has increased over the past few years due to the existence of Social Network Services like Facebook, Instagram, Twitter, etc., a trend that paves the way for fresh and creative methods to forge an image for a make believe and gain favorable impressions. The tampering of images through forgery influences the perception an observer has of the depicted scene, potentially resulting in ill consequences if created with malicious intentions. This problem poses a need to verify the authenticity of images originating from unknown sources. This project serves to conduct an experimental investigation using a series of designed methodologies and algorithms like SIFT (Scale Invariant Features Transform), RANSAC (Random Sample Consensus) to identify a digital image forgery called copy-­‐move forgery. As the name suggests, this forgery is executed by copying an area of an image pasted onto another zone to create duplication or to cancel something that was not needed. By applying such methods and algorithms, we are able to tell whether a copy-­‐move attack has occurred and furthermore, to recover the geometric transformation used to perform cloning. The results and performances of the implementation will be described in the later part of this report.