FISH: Face Intensity-Shape Histogram representation for automatic face splicing detection

Tampered images spread nowadays over any visual media influencing our judgement in many aspects of our life. This is particularly critical for face splicing manipulations, where recognizable identities are put out of context. To contrast these activities on a large scale, automatic detectors are required. In this paper, we present a novel method for automatic face splicing detection, based on computer vision, that exploits inconsistencies in the lighting environment estimated from different faces in the scene. Differently from previous approaches, we do not rely on an ideal mathematical model of the lighting environment. Instead, our solution, built upon the concept of histogram-based features, is able to statistically represent the current interaction of faces with light, untied from the actual and unknown reflectance model. Results show the effectiveness of our solution, that outperforms existing approaches on real-world images, being more robust to face shape inaccuracies.