Rey’s Ornament Image investigation – ROIi

The aim is to create a database of ornaments extracted from works published in the 18th century by Marc Michel Rey and to jointly develop an image analysis useful for the authentication of books by this publisher known for his role in the dissemination of Enlightenment thought.
The images were collected by automatic extraction from digitised books, categorised and then verified manually. The database was created with Heurist and the metadata is integrated (bibliographic and description data). An operational system for navigating the database is in place.
The image search engine VISE has been implemented and allows first image comparisons. VISE is equipped with an image-query versus image-find comparison module with display of matches. It is also equipped with a visualisation module reduced to the alternate display of the two images. Work on image grouping, particularly for compound ornaments, is underway.
For the computer vision part: Development of a model based on an auto-encoder for the detection of anomalies, more precisely differences in design between a request and the occurrences of a similar motif in the database, and creation of a mode of visualisation of such differences by transparency, which can be integrated into the visualisation module.

The models thus developed are intended to be implemented within a demonstrator comprising a viewer dedicated to the perception of the details resulting from the automatic detection.

Creation of a database of ornaments with Heurist Huma-num; beta version).
Implementation of the VISE image search engine (VGG Oxford) on the virtual machine.
Development of an autoencoder-based model for anomaly detection
Organisation of a workshop and an interdisciplinary and international study day: Issues and methods of analysis of ancient ornaments with the support of the CNRS APPAMAT GDR. 15-16 June 2022: available online:
www.youtube.com/watch
Communication at the DH2022 Congress

The database of ornaments used by Marc Michel Rey will be published in open access, on a site hosted by the TGIR Huma-Num. Together with the scientific publications related to the project, it will allow us to advance knowledge on the practices and policies of the book under censorship. Moreover, all our results (methodology, thesaurus) will be published under a licence (CC-BY) authorising their sharing and reuse.
In addition to the publication of an unpublished collection of ornaments used by the bookseller Marc Michel Rey, the project's challenge is to bring the tools designed for the detection of anomalies to larger databases.

1. Novelty detection and visualization in old ornaments, S. Steinlin, F. Vial-Bonacci, S. Chaki, C. Bahier-Porte ,and T. Fournel in CCIW June 9, 2022 (on line ; gdr-appamat.cnrs.fr/evenements-passes/9-10-june-2022-computation-color-imaging-workshop-2022/)
2. Computer Vision for the Study of Printers' Ornaments and Illustrations in European Hand-Press Books by Bahier-Porte, Christelle; Bergel, Giles; Dutta, Abhishek; Fournel, Thierry; Thomas, Drew; Vial-Bonacci, Fabienne; Wilkinson, Hazel; Andrew, Zisserman; Loïc, Denis; Emonet, Rémi; Habrard, Amaury; Ventresque, Vincent; Gautrais, Thomas in Digital Humanities Conference 2022, Pannel 3-01, July 27, 2022
3. Khan M. S., Emonet R. et Fournel T., Vignette detection and reconstruction of composed ornaments with a strengthened autoencoder, hal.archives-ouvertes.fr/hal-03409930, 2021

The ROIi (Rey's Ornament Image investigation) project brings together researchers in the fields of the history of ideas, literature and the history of books (Ihrim) on the one hand, and computer vision and machine learning (Hubert Curien Laboratory) on the other. The aim of this collaborative and interdisciplinary project is to design a tool to help authenticate books published under fictitious or counterfeit names or addresses in the 18th century, through the analysis of ornaments. It is based on the design of a database of ornaments used by the bookseller Marc Michel Rey (1720-1780). The editorial and commercial practices of this French-speaking bookseller based in Amsterdam are indeed particularly representative of both the typographical uses of ornaments and the strategies for circumventing censorship. The study of these editorial strategies is enlightening in order to understand the booktrade system and the way in which the sharing of knowledge and ideas on a European scale was practised at a time when it was beginning to be defended philosophically. These strategies make it particularly difficult to attribute a work to a publisher and to distinguish between genuine and counterfeit works. The investigation of ornaments then constitutes an additional clue to identify the works, within a cluster of concordant clues. The database will thus be associated with an anomaly detection task, combining computer vision and automatic learning. The objective is to design a decision support tool likely to reveal differences in shape at the level of wood ornaments and the publisher's mark, and differences in typographic style at the level of compound ornaments, based on the content of the database's data. Patch detection and auto-encoding will be developed to be confronted or combined in order to deliver tangible visual elements on demand, with patch analysis approximating the mechanisms implemented during a visual comparison of facing images, the auto-encoders producing an efficient representation of the data in unsupervised mode. This tool will be blindly tested on collections of ornamental images attributed to Marc Michel Rey, but also on fakes recognized by experts, before being tested online and in open access, and eventually transferred from Marc Michel Rey's collection to other heritage collections.