Algorithms for Film Digital Restoration: Unsupervised Approaches for Film Frames Enhancement

Since the beginning of this century we are assisting to a crucial step in the domain of cinema: the transition from analogic to digital. The computed generated imagery substituted the early developed special effects on film and the use of smartphones and digital devices took the place of old Super8 formats. In this context, film restoration passes quite often by the digitization and the use of software for image enhancement and restoration is widely diffused and used also by non-pro users. The digital restoration of colour has widely spread, and digital techniques allow the easy removal of colour casts, frames histograms equalization, dynamic range expansion and saturation adjustment. Despite this easy applicability, when adjusting the colour of a film of historical value, constant supervision by qualified personnel is still required. Digitization projects impose the acquisition of the single frames of a film through scanners that transform the film media in numerical data codified through specific codec that can be lossless or lossy. The following step concerns the use of specific software for film restoration that work on the acquired data. Consequently, the elaborations, modifications and enhancements that can be made on any frame are limitless and reversible. Despite the great potential that the image enhancement offers, the digital restoration and colour correction is still in the hands of few software producers and the academic research developed for different kinds of application (i.e. natural images, satellite images, underwater imaging, smartphones applications, etc.), and just a few works concerns film restoration applications.1 The need of improving the research and experiment image enhancement for movie frames enhancement is fundamental because it could lead to costs reduction and to trustworthy results. With this contribution we aim at discussing some issues in digital restoration. In the following discussion we purpose the use of a specific family of unsupervised algorithms for image restoration inspired by the capabilities of Human Visual System (HVS): the Spatial Colour Algorithms (SCAs).