A robust technique for copy-move forgery detection and localization in digital images via stationary wavelet and discrete cosine transform

In this era, due to the widespread availability of digital devices, various open source and commercially available image editing tools have made authenticity of image contents questionable. Copy-move forgery (CMF) is a common technique to produce tampered images by concealing undesirable objects or replicating desirable objects in the same image. Therefore, means are required to authenticate image contents and identify the tampered areas. In this paper, a robust technique for CMF detection and localization in digital images is proposed. The technique extracts stationary wavelet transform (SWT) based features for exposing the forgeries in digital images. SWT is adopted because of its impressive localization properties, in both spectral and spatial domains. More specifically approximation subband of the stationary wavelet transform is utilized as this subband holds most of the information that is best suited for forgery detection. The dimension of the feature vectors is reduced by applying discrete cosine transform (DCT). To evaluate the proposed technique, we use two standard datasets namely, the CoMoFoD and the UCID for experimentations. The experimental results reveal that the proposed technique outperforms the existing techniques in terms of true and false detection rate. Consequently, the proposed forgery detection technique can be applied to detect the tampered areas and the benefits can be obtained in image forensic applications.