Detecting tampered regions in digital images using discrete cosine transform and singular value decomposition

作者：Kang Xiaobing^*; Lin Guangfeng; Chen Yajun; Zhang Erhu; Duan Ganglong

来源：International Journal of Digital Content Technology and Its Applications, 2012, 6(23): 179-188.

DOI：10.4156/jdcta.vol6.issue23.21

• Additive Gaussian white noise
• Detection methods
• Digital image
• Dimensionality reduction
• Gaussian blur
• Geometric manipulation
• Geometrical transformation
• Image forensics
• Image tampering
• JPEG compression
• Passive detection
• Region duplication forgery
• Single images
• Special objects
• Techniques used

Region duplication is a simple and common form of image tampering used to hide or clone special objects in a single image scene. In this paper, we describe a novel detection method for region duplication forgery that automatically detects and localizes tampered regions in digital images using discrete cosine transform(DCT) and singular value decomposition(SVD). DCT is applied to each block to represent its features resisting typical geometric manipulations. SVD is used for improving the ability on resisting noise and dimensionality reduction. Comparisons with the existing methods by experimental works indicate that the proposed algorithm is more robust against some common postprocessing operations or attacks such as typical geometrical transformations, lossy JPEG compression, additive Gaussian white noise and Gaussian blur filtering. These operations and distortions are currently techniques used to conceal traces of region duplication forgery in digital images.

• 出版日期2012