A Proposed Workflow for the Restoration of Image Artifacts in Forensic Applications

Closed-Circuit Television recordings are widely used in forensic science. However, the acquired images often need to be restored using several image processing techniques. The order and methods by which these techniques are applied substantially impact the final result. In this work, we focus on the case of an image affected by a combination of optical/motion blur, perspective distortion, and additive noise. We give theoretical support for selecting the best-performing workflow and provide numerical results and experiments on real degraded images validating the proposed workflow.