Automated Edge Detection for Cultural Heritage Conservation: Comparative Evaluation of Classical and Deep Learning Methods on Artworks Affected by Natural Disaster Damage

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This paper explores a highly relevant and novel topic: automating edge detection in cultural heritage protection by using image processing and deep learning technologies, especially on artworks damaged by natural disasters. The research was conducted within the framework of the ChemiNova project, integrating interdisciplinary collaboration (computer science and art conservation), and it is a very meaningful study. Before the paper is published, I think there are still several issues that need to be clarified. Here are my comments:
The author proposed to conduct research using deep learning methods, but some F1 values are relatively low. The author needs to provide detailed explanations for these phenomena
2. The experiment was based on four artworks from Valencia pilot (all from the Martinez Guerricabeitia collection), with a small sample size and a lack of diversity (such as not covering architectural scales or more types of disasters). This may lead to result bias.
3. The paper emphasizes the advantages of automation but does not address the actual deployment obstacles. The author can elaborate on the computational costs of steps such as preprocessing

Author Response

We sincerely thank Reviewer 1 for their insightful comments and suggestions. Please note that detailed responses to each individual comment have been provided directly within the attached Word document.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

1. Supplement image resolution and hyperspectral band range of the 4 artworks in the dataset.
2. Clarify the annotation process of "ground truth" and expert consistency checks.
3. Add computational time comparison of different edge detection algorithms.
4. Discuss applicability of results to other art forms like sculptures and murals.
5.  Modify "translucent manner" to "semi-transparent way" for proper collocation.
6. Replace the comma in "heritage, it’s easy" with a semicolon to fix grammar.
7. Unify "alteration mapping" and "damage mapping" as "damage mapping".
8. Add recent studies (post-2020) on deep learning in cultural heritage protection.
9. Supplement literature on how climate disasters affect artwork materials.
10. Correct format errors in Table 1 for "El nuevo orden mundial" entries.

11. I think these two documents are worth reading for the authors, as they will be helpful in enriching the content of the article. Yanqin Li, Dehai zhang. Toward Efficient Edge Detection: A Novel Optimization Method Based on Integral Image Technology and Canny Edge Detection [J]. Process，2025,13（293）：1-18 ，

     Zhang Dehai, Li, Junheng, Zhu Huimin, et al. The Researches and Applications of Reverse Engineering in the   Protection and Inheritance of National Handcrafts [J]. Nanoscience and   Nanotechnology Letters, 2020,12（9）：1063-1069.

Author Response

We would like to express our sincere gratitude for your thoughtful and constructive feedback. Your comments have been invaluable in helping us improve the quality and clarity of our manuscript. A detailed point-by-point response to each of your observations has been included in the attached Word document, where we have also highlighted the corresponding changes made in the text.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

I believe that the author's revisions have basically addressed my review comments. On the premise of meeting the editor's requirements, I think it is acceptable.