We would like to inform you about an article written by Marco Roling, which has been published in March 2020 and is dedicated to experiments about the HTR-processing of documents with low standard of preservation and legibility. The tests have been carried out on documents with different levels of archival damage in order to check, how Handwritten Text Recognition can deal with that. Moreover, some ideas are presented on how the probability of good HTR-performance can be predicted.
This is the link to the online resource, if you would like to read the whole article: https://www.researchgate.net/publication/340117708_Does_Handwriting_Text_Recognition_Work_for_Damaged_Archives