A novel method for detecting light source for digital images forensic

Abstract

Manipulation in image has been in practice since centuries. These manipulated images are intended to alter facts — facts of ethics, morality, politics, sex, celebrity or chaos. Image forensic science is used to detect these manipulations in a digital image. There are several standard ways to analyze an image for manipulation. Each one has some limitation. Also very rarely any method tried to capitalize on the way image was taken by the camera. We propose a new method that is based on light and its shade as light and shade are the fundamental input resources that may carry all the information of the image. The proposed method measures the direction of light source and uses the light based technique for identification of any intentional partial manipulation in the said digital image. The method is tested for known manipulated images to correctly identify the light sources. The light source of an image is measured in terms of angle. The experimental results show the robustness of the methodology.

A Neural Network for Interpolating Light-Sources

“…For the sake of clarity, it is worth stressing that non CNNbased light direction methodologies as e.g. those in [20], [21] have purposely been excluded from the comparison due to their differing approaches, when compared against the CNN approach as explained in section I.…”

“…It is worth noting that there are also a number of non-CNN-based light direction methodologies [20], [21], [22], [23], [24]. However, these have become exceedingly rare in comparison to CNNs and are similar to illumination-models found in shader-based computer graphics applications, such as standardised normal maps and Blinn-Phong-based illumination-models [25].…”