Preserving the Past with Deep Learning-Based Damage Detection in Ancient Manuscripts and Artworks
Bibliographic record
Abstract
Safeguarding ancient manuscripts and artworks is essential for conserving collective human memory. However, these unique objects are increasingly endangered by environmental stressors, biochemical decay, and inadvertent human error. This contribution introduces an advanced deep learning framework for precise damage localization and characterization in digitized heritage materials, thereby overcoming the scalability constraints of conventional, labour-intensive inspection methods. Our architecture reconciles convolutional feature extraction with attention driven cortical refinement, empowering the system to segment and categorize decay signatures, including pigment bleed, ink reduction, mechanical tears, and fungal biodeterioration. Validation is conducted on an annotated collection of high-resolution manuscript and image-survey data, wherein the algorithm yields an overall detection precision of 94.8%, recall of 93.2%, and balanced$\mathbf{F 1}$-score of$\mathbf{9 4. 0 \%}$, superseding industry standard U-Net and ResNet classifiers. Notably, the performance remains consistently high across heterogeneous artifact typologies and chronological strata. This study thus reinforces intelligent automation in heritage conservation and proposes a replicable framework that integrates early-surveillance feedback into digital archivists' and conservators' decision-making canon.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".