2011 · 190 citations · 15 references
ComputingInformation TechnologyComputer VisionDigital ForensicsDigital ImagingComputer ForensicsDigital Image ProcessingDuplicate DetectionForgery DetectionCopy-move Forgery DetectionDigital ForgeriesDigital Image AnalysisDuplicate Image DetectionForensicsImage ForensicsImage Forgery Detection
Digital images are widely used but can be easily tampered, making authenticity verification a key challenge in image forensics, especially for copy‑move forgery. The study proposes a method to detect copy‑move forgery using SURF features and KD‑Tree matching. The method extracts SURF descriptors and matches them via a KD‑Tree to identify duplicated regions. The approach successfully detects copy‑move forgery in high‑resolution images.
An Image would yield better impact in convincing someone of something rather than pure description by words. Digital images are widely used in various fields like medical imaging, journalism, scientific manipulations and digital forensics. However, images are not reliable as it may be. Digital images can be easily tampered with image editing tools. One of the major problems in image forensics is determining if a particular image is authentic or not. Digital image forensic is an emerging field of image processing area. Copy-move forgery is one type of image forgery in digital image forensic where various methods have been proposed in the field to detect the forgery. In this paper a technique is presented to detect Copy-Move Forgery based on SURF and KD-Tree for multidimensional data matching. We demonstrate our method with high resolution images affected by copy-move forgery.
15
Speeded-Up Robust Features (SURF)
Herbert Bay, Andreas Ess, Tinne Tuytelaars et al. · Computer Vision and Image Understanding · 2008 · 13.4K citations
Detection of Copy-Move Forgery in Digital Images
Jessica Fridrich · 2004 · 992 citations