Tampered region detection of inpainting JPEG images

Abstract

Image inpainting, the technique of modifying an image in an imperceptible form, is a usually used image tampering method to remove particular objects. In this paper, a novel passive detection method for inpainting-tampered JPEG images is proposed when the tampered image is saved in an uncompressed format or in the JPEG compressed format. We detect the tampered region by computing and segmenting the averaged sum of absolute difference images between the tampered image and a resaved JPEG compressed image at different quality factors. Experimental results show that the proposed method can detect and locate the inpainting-tampered region efficiently and accurately when an inpainting image is saved in an uncompressed format or in JPEG compressed format of higher quality than the original JPEG image quality, and that the proposed method has better detection performance than the existing three methods.