Method of photomontage detection under conditions of limitations absence for photos falsification

Abstract

The widespread using of fake pictures in information wars, lawsuits, politics, etc., needs to develop a new detection methods of photomontage that effective without the expert. One is a method of photomontage identifying based on the analysis of singular values of matrix blocks of digital images. Aim: The aim of this research is to check the field of application of photomontage detection method based on analysis of singular values of matrix blocks of digital images, in the absence of restrictions on their compression ratio. Materials and Methods: The basis of this method is to identify the differences between the images when they have different compression ratios: the matrix of zero singular values of blocks corresponding to foreign 'part of images. We distinguish this area on the background of the main image that allows you to detect falsification. The above method was investigated under certain restrictions imposed on the used test photos. An advanced experiment with images was held, for which there are no restrictions on the compression ratio. Results: In experiment the falsification was detected in 44.4% of cases while maintaining the digital image after photomontage in lossless format, and 53.3% - in lossy. Most often the montage was detected when the difference between the quality factor Q of the main image and the replacing area was more than 2.