Thesis Description & Objectives
This thesis project is part of the European COST Action LEAF (Leonardo da Vinci’s European Academic Network). Leonardo’s manuscript corpus is currently fragmented and preserved across various international institutions (e.g., Biblioteca Ambrosiana, Royal Collection at Windsor, Louvre, Victoria and Albert Museum).
The goal of this thesis is to design and develop Computer Vision and Machine Learning models capable of analyzing high-resolution digitized documents to suggest possible “matches” (correspondences) between different fragments, including the analysis of front-to-back (recto-verso) consistency.
The work focuses on creating the “intelligence engine” that will interface with a web-based visualization platform (not the subject of this thesis). The model will leverage historiographical features (e.g., dating) and physical/geometrical characteristics (chain lines, segmentation, dimensions, edge shapes, and fiber/stroke continuity) to obtain probabilistic match suggestions. The system will act as an intelligent assistant to reduce the search space for scholars, ensuring that every proposed union is physically possible on both sides of the sheet.
Technical Details and Development Path:
The student will work on developing an analysis module based on state-of-the-art techniques, including:
– State-of-the-art analysis: Review of similar models and applications in the field.
– Dataset preparation, pre-processing, and Multimodal Feature Extraction.
– Recto-Verso Matching Models: Experimentation with existing architectures to be potentially specialized (e.g., CNNs, Siamese Networks, Vision Transformers, Hybrid Models).
– Suggestion API Development: Support for interfacing the model via microservices (e.g., FastAPI) for integration with the visualization frontend.
– Expert Validation: Testing model suggestions on real-world use cases provided by the LEAF network to measure accuracy and practical utility.
Professional Value for the Student
This proposal is ideal for students wishing to enrich their portfolio with a concrete example by tackling a real-world CV/ML/AI problem. The thesis offers:
– Experience in Computer Vision (CV/ML): Working on real images with historical degradation and multi-face analysis.
– Scientific Impact: Contribution to an international project of excellence on Leonardo’s heritage.
– High-Level Interdisciplinary Collaboration: Interaction with the European COST LEAF network and engagement with international specialists (art historians, codicologists, technologists, and conservators).
– Applied AI: Translating complex models into functional APIs for professional workflows.
