Image splicing detection using Gaussian or defocus blur

The availabilty of Image manipulation softwares such as Photoshop, has made it easier to forge images than ever before. In this work, we tackle a particular kind of image forgery called Image Splicing. In Image Splicing, an artificial region may be introduced in an image so as to alter its content. We address Image Splicing in natural images with inherent Gaussian blur. We hypothesize that the forged region introduced may have standard deviation different from the rest of the image or may have a different type of blur altogether. We aim to expose such imbalances in blur by first de-blurring the images and using ringing effects. The ringing effects, provide useful cues as to potential forgeries.