Digital image copy-move forgery detection based on discrete fractional wavelet transform

Abstract

With the advancement of sophisticated cameras and image editing software tools, digital image tampering techniques are frequently used without leaving visual cues behind. Digital image copy-move forgery is a kind of image manipulation that involves copying and pasting of a certain section (or sections) within the same digital image. Generally, this is done with false intentions of hiding important information or providing false information in an image. In view of this, the focus of the present paper is to propose a discrete fractional wavelet transform-based scheme for identification of duplicated regions in the image. The test image is split into overlapping image blocks with fixed dimensions. Then, on each image block, discrete fractional wavelet transform is employed for the extraction of their features. All the feature vectors are systematized in lexicographical manner followed by the block matching and block filtering steps to obtain the replicated blocks, if any. The proposed method can detect single and multiple duplicated regions successfully. The results are compared to existing techniques based on precision and recall parameters. Simulation results show that the proposed forgery detection scheme can detect tampering areas even in the presence of distortions due to Gaussian blurring and JPEG compression.