Learning images using compositional pattern-producing neural networks for source camera identification and digital demographic diagnosis

In this work, we propose a neural network based framework to explore the statistical correlation intrinsically embedded due to interpolations in a relatively small neighborhood, in which the interpolation process is cognized from the interpolation results and the spatially invariant stylized computational rules in interpolation algorithms are simulated and learned by adjusting weights and bias values of neural networks. Experiments show that, our approach is competitive among the state of the art of source camera identification methods. It is also effective for digital forgery detection and other interesting experiments such as the digital demographic diagnosis and prediction. The framework can also be applied to other types of image interpolations such as super-resolution.

► A framework to explore statistical correlations embedded due to interpolations.
► Competitive among the state of the art of source camera identification methods.
► Effective digital forgery detection.
► The digital demographic diagnosis and prediction.