Image Forensics Using Error Level Analysis and Block Matching Methods

The development of image editing tools today makes everyone able to manipulate images easily so that many images are doubtful of their authenticity. The current image can be used as evidence in a legal case in court. The authenticity of the image is a topic that many have tried to solve various studies. This study discusses the authenticity of the image using the Error Level Analysis (ELA) method to determine the authenticity of the image, especially in the JPEG image. Block Matching is used in the process of dividing an image into several square or block parts. The ELA method has been successfully implemented with 95% image compression resulting in MSE and PSNR values ​​in distinguishing the edited image. The average MSE is 23.8 dB and the average PSNR is 34.47 dB. Block Matching results as a whole show that the pixel value for x values ​​that reach 30 there are 9 images, x values ​​that reach 24 there are 9 images, x values ​​that reach 23 there are 1 image, and for x values ​​that reach 19 there is 1 image. The result of pixel (y) of all images exceeds the value of 12 which in pixel (y) undergoes many changes marked by the presence of white spots.