Deep Learning on Digital Image Splicing Detection Using CFA Artifacts

Digital image forgery is a serious problem of an increasing attention from the research society. Image splicing is a well-known type of digital image forgery in which the forged image is synthesized from two or more images. Splicing forgery detection is more challenging when compared with other forgery types because the forged image does not contain any duplicated regions. In addition, unavailability of source images introduces no evidence about the forgery process. In this study, an automated image splicing forgery detection scheme is presented. It depends on extracting the feature of images based on the analysis of color filter array (CFA). A feature reduction process is performed using principal component analysis (PCA) to reduce the dimensionality of the resulting feature vectors. A deep belief network-based classifier is built and trained to classify the tested images as authentic or spliced images. The proposed scheme is evaluated through a set of experiments on Columbia Image Splicing Detection Evaluation Dataset (CISDED) under different scenarios including adding postprocessing on the spliced images such JPEG compression and Gaussian Noise. The obtained results reveal that the proposed scheme exhibits a promising performance with 95.05% precision, 94.05% recall, 94.05% true positive rate, and 98.197% accuracy. Moreover, the obtained results show the superiority of the proposed scheme compared to other recent splicing detection method.