Substantial parts of the image material of today’s digital archives are of low quality, creating problemsfor automated processing using machine learning. These quality issues can stem from a multitude ofreasons, ranging from damaged originals to the reproduction hardware. Modern machine learninghas made automatic “restoration” or “colourization” readily available. Curators and scholars mightwant to “improve” or “restore” the original’s quality to create engagement with the artefacts. However,a fundamental problem of the “restoration” process is that information must always be added to theoriginal, creating reproductions with a synthesized extended realism.
In this paper, we will discuss the nature of the “restoration” or “colourization” process in two parts.Firstly, we will focus on how the restoration algorithms work, discussing the nature of digital imageryand some intrinsic properties of “enhancement”. Secondly, we propose a system, based on modernmachine learning, that can automatically “improve” the quality of digital reproductions of handwrittenmedieval manuscripts to allow for large scale computerized analysis. Furthermore, we provide code forthe proposed system. Lastly, we end the paper by discussing when and if “restoration” can, and should,be used.