Reference-free Image Quality Evaluation for Digital Film Restoration

Abstract

Motion pictures represent an important cultural heritage. As films age they became prone to all kinds of defects such as dust, scratches, vinegar syndrome and dye fading, some of which are chemically irreversible processes. The quality of a restored movie tends to be estimated subjectively by experts. On the other hand, objective quality metrics do not necessarily correlate well with perceived quality. Digital restoration methods are now being developed which can argument traditional photochemical restoration techniques, or even address problems that are out of the reach of traditional methods. Also digital restoration has the advantage of not affecting the original material, since it works on a digital copy. Digital restoration techniques are becoming increasingly automated but restoration evaluation of their efficacy remains still a rarely tackled issue. This paper outlines some reference-free image quality metrics for photographs and digital film restoration. The metrics can assess some intricate defects in frames and sequences such as colour-fades films with more than one colour cast (two or more dominant colours). They permit the evaluation process to be speeded up. These measures can be used also to characterise an image sequence before its processing in order automatically fine tune the parameters of the restoration techniques.