Thursday May 23 – Program details coming soon.
Image quality is the combination of significant attributes of an image depending by its application and weighted for the human perception. It is part of the experience measures and is still a hot topic in image enhancement and image processing. Since nowadays different metrics have been developed and the aim of many of them is to find a single number to assess the quality of an image. Some of those metrics are based on mathematical measures of contrast, colour distribution, luminance, and some others are high-level metrics that tries to simulate the behaviour of the human visual system to assess quality. The main problem is that a single measure does not suffice to capture and numerically summarize all the aspects concurring to image quality. In addition, different measures return different quality values for the same images that disagree between them.
In this context, trying to assess the quality of a film restoration is often harder, because in this application filological constraints and lack of reference aim are a difficult challenge for automatic evaluation. However, the world of film restoration is subject to a fast technical growth and the quality evaluation is often in the hands of a single curator.
In this presentation we purpose a different point of view of film restoration quality assessment: the diagnostic of the frame. As the analog film is subject to an accurate analysis of the materials and conservation status, also for the digital image we should apply the same procedure. The quality of a restored frame should be assessed through different health levels and indicators. Here we will present a first application of levels that could assess the quality of frames restored though different techniques.