As screenshots of copyrighted video content are spreading through the Internet without any regulation, cases of\r\ncopyright infringement have been observed. Further, it is difficult to use existing forensic techniques for\r\ndetermining whether or not a given image was captured from a screen. Thus, we propose a screenshot\r\nidentification scheme using the trace of screen capture. Since most television systems and camcorders use\r\ninterlaced scanning, many screenshots are taken from interlaced videos. Consequently, these screenshots contain\r\nthe trace of interlaced videos, combing artifacts. In this study, we identify a screenshot using the characteristics of\r\ncombing artifacts that appear to be shaped like horizontal jagged noise and can be found around the edges. To\r\nidentify a screenshot, the edge areas are extracted using the gray level co-occurrence matrix (GLCM). Then, the\r\namount of combing artifacts is calculated in the extracted edge areas by using the similarity ratio (SR), the ratio of\r\nthe horizontal noise to the vertical noise. By analyzing the directional inequality of noise components, the\r\nproposed scheme identifies the source of an input image. In the experiments conducted, the identification\r\naccuracy is measured in various environments. The results prove that the proposed identification scheme is stable\r\nand performs well.
Loading....