Detection of Image Splicing using Illuminant Color Estimation

Digital image forensics is a set of techniques used for digital image forgery detection and is widely used to certify the content or the authenticity of a document. The splicing operation, which crops and pastes one or several regions from separate images, is a common technique used for image forgery. In the literature, most image forgery detection techniques are based on machine learning. Only a few methods take advantage of physical features to detect the tampering. In this paper, we propose a new method to detect image splicing from an analysis of regions of interest in the uv chromaticity space. Their pixels are compared to the Planckian locus and the closest ones, seen as achromatic, are stored in a weighted histogram depicting Gaussian distribution. After a selection of the suitable Gaussians, the illuminant color is estimated. Results on spiced images are presented and discussed