Adobe Photoshop and Eighteenth-Century Manuscripts: A New Approach to Digital Paleography
Bibliographic record
Abstract
While research coordinator at the Burney Centre at McGill University in Montreal, I pioneered new digital paleographical methods to support the editorial work on Frances Burney and Samuel Richardson undertaken there. Prior to my interventions, the primary method for reading faint, obscured, and obliterated manuscript texts had been multi-spectral imaging, which is prohibitively expensive, limiting its utility as a general research tool, although it is still sometimes in use. There have not been many alternative digital paleographical methodologies. The potential of image manipulation software, such as Adobe Photoshop, has been noted by a few scholars, but not explored. Working in Adobe Photoshop, I have developed a method of deciphering heavily deleted or obliterated text through the use of layering techniques, altered color levels, and the employment of certain kinds of filters. The method is more advanced than simple image enlargement techniques used by most researchers. Importantly though, it remains far less expensive than multi-spectral imaging. The technique contributed to the recovery of nearly all of the obliterated text in the first two volumes of The Court Journals and Letters of Frances Burney, which were published by Oxford University Press in 2011, and it was also used within in-progress volumes from The Cambridge Edition of the Works of Samuel Richardson. This article discusses the methodology and some of its key results from eighteenth-century manuscripts.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.017 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.009 | 0.007 |
| Science and technology studies | 0.004 | 0.007 |
| Scholarly communication | 0.015 | 0.012 |
| Open science | 0.002 | 0.006 |
| Research integrity | 0.002 | 0.005 |
| Insufficient payload (model declined to judge) | 0.032 | 0.011 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".