Forgery detection using multiple light sources for synthetic images

Abstract

Image processing requires an estimation of position, direction and illumination of the objects present in a scene. Nowadays, digital image manipulations have experienced a remarkable growth. These image manipulations can be detected by various forgery detection techniques that have been developed in the past few years. We describe a forgery detection technique based on estimations of multiple light source directions. This method uses a pixel patch from the image region to estimate the source light vector. The implementation is done for images where one and more light sources are available in the scene. The proposed technique is able to identify image forgery in terms of elevation angle α obtained from a source of light and surface normal. This method is tested for both outdoor and indoor images under certain known parameters. The novelty of our method is that photo manipulation detection is done using a multiple light source detection approach. We demonstrate that the proposed technique produces accurate results by making certain assumptions about surface properties and illumination parameters.