Digital image splicing detection based on approximate run length

Image splicing is very common and fundamental in image tampering, which severely threatens the integrity and authenticity of images. As a result, the detection of image splicing is of great importance. In this paper, an approximate run length based scheme is proposed to detect this specific artifact. Firstly, the edge gradient matrix of an image is computed, and approximate run length is calculated along the edge gradient direction. Then, some features are constructed from the histogram of the approximate run length. To further improve the detection accuracy, the approximate run length is applied on the predict-error image and the reconstructed images based on DWT to obtain more features. Finally, support vector machine (SVM) is exploited to classify the authentic and spliced images using the constructed features. The experiment results demonstrate that the proposed approach can achieve a relatively high accuracy with less computational cost and fewer features when compared with other methods.

► An approach based on approximate run length is proposed for splicing detection.
► A novel “approximate run length” is developed by making improvements to the original one.
► Approximate run length based method is applied on images to construct features.
► The method is also applied on predict-error image and reconstructed images novelly.
► The approach is proved to be effective and efficient by experimental results.