One common task in image forensics is to detect spliced images, where multiple source images are composed to one output image. Most of the currently best performing splicing detectors leverage high-frequency artifacts. However, after an image underwent strong compression, most of the high frequency artifacts are not available anymore. In this work, we explore an alternative approach to splicing detection, which is potentially better suited for images in-the-wild, subject to strong compression and downsampling. Our proposal is to model the color formation of an image. The color formation largely depends on variations at the scale of scene objects, and is hence much less dependent on high-frequency artifacts. We learn a deep metric space that is on one hand sensitive to illumination color and camera white-point estimation, but on the other hand insensitive to variations in object color. Large distances in the embedding space indicate that two image regions either stem from different scenes or different cameras. In our evaluation, we show that the proposed embedding space outperforms the state of the art on images that have been subject to strong compression and downsampling. We confirm in two further experiments the dual nature of the metric space, namely to both characterize the acquisition camera and the scene illuminant color. As such, this work resides at the intersection of physics-based and statistical forensics with benefits from both sides.

The detection of images that are spliced from multiple sources is one important goal of image forensics. Several methods have been proposed for this task, but particularly since the rise of social media, it is an ongoing challenge to devise forensic approaches that are highly robust to common processing operations such as strong JPEG recompression and downsampling.In this work, we make a first step towards a novel type of cue for image splicing, which is based on the color formation of an image. We make the assumption that the color formation is a joint result of the camera hardware, the software settings, and the depicted scene, and as such can be used to locate spliced patches that originally stem from different images. To this end, we train a two-stage classifier on the full set of colors from a Macbeth color chart, and compare two patches for their color consistency. Our preliminary results on a challenging dataset on downsampled data of identical scenes indicate that the color distribution can be a useful forensic tool that is highly resistant to JPEG compression.