Copy-move forgery detection through stationary wavelets and local binary pattern variance for forensic analysis in...

Area of Science:

• Digital Image Forensics
• Computer Vision
• Signal Processing

Background:

• Image tampering, particularly copy-move forgery, poses a significant threat to image integrity in critical applications.
• The visual similarity of duplicated regions makes detection challenging for conventional methods.
• There is a need for robust techniques to validate image authenticity and identify manipulated areas.

Purpose of the Study:

• To propose an efficient and robust copy-move forgery detection (CMFD) technique.
• To enhance the reliability of image authentication in proof-critical domains.

Main Methods:

• The proposed CMFD technique utilizes local binary pattern variance (LBPV) applied to low approximation components derived from stationary wavelets.
• The method processes circular regions to better handle post-processing operations like rotation and scaling.
• Evaluation involved comprehensive testing on CoMoFoD and Kodak lossless true color image (KLTCI) datasets.

Main Results:

• The proposed CMFD technique demonstrated superior performance compared to existing state-of-the-art methods.
• Effective detection of forged regions was achieved even in the presence of various image manipulations including translation, flipping, blurring, rotation, scaling, color reduction, and brightness changes.
• The technique proved robust against multiple forged regions within a single image.

Conclusions:

• The developed CMFD technique offers a reliable solution for detecting copy-move image forgeries.
• The method has significant potential applications in journalism, law enforcement, judiciary, and other fields requiring high image integrity.