Large-image Object Detection for Fine-grained Recognition of Punches Patterns in Medieval Panel Painting
🤖 AI Summary
This study addresses the challenge of automatically detecting minute, densely packed, and repetitive punch marks in 13th–14th-century Tuscan panel paintings. We propose a fine-grained pattern detection method tailored for ultra-large, high-resolution art images. Methodologically, we adapt YOLOv10—the first such application in art-historical computer vision—integrated with sliding-window tiling, a custom overlap-suppression fusion strategy, and domain-specific pre- and post-processing pipelines. Evaluated on authentic large-scale panel painting imagery, our approach significantly improves punch localization accuracy and robustness against image degradation and scale variation. The resulting system constitutes the first reproducible, deployable quantitative tool for punch-based attribution analysis in art history. It enables systematic, objective comparison of artisanal techniques across workshops and periods, thereby advancing the field toward greater methodological rigor, standardization, and computational reproducibility.
Application Category
📝 Abstract
The attribution of the author of an art piece is typically a laborious manual process, usually relying on subjective evaluations of expert figures. However, there are some situations in which quantitative features of the artwork can support these evaluations. The extraction of these features can sometimes be automated, for instance, with the use of Machine Learning (ML) techniques. An example of these features is represented by repeated, mechanically impressed patterns, called punches, present chiefly in 13th and 14th-century panel paintings from Tuscany. Previous research in art history showcased a strong connection between the shapes of punches and specific artists or workshops, suggesting the possibility of using these quantitative cues to support the attribution. In the present work, we first collect a dataset of large-scale images of these panel paintings. Then, using YOLOv10, a recent and popular object detection model, we train a ML pipeline to perform object detection on the punches contained in the images. Due to the large size of the images, the detection procedure is split across multiple frames by adopting a sliding-window approach with overlaps, after which the predictions are combined for the whole image using a custom non-maximal suppression routine. Our results indicate how art historians working in the field can reliably use our method for the identification and extraction of punches.
Problem
Research questions and friction points this paper is trying to address.
Machine Recognition
13th-14th Century Italian Paintings
Seal Feature Extraction
Innovation
Methods, ideas, or system contributions that make the work stand out.
Computer Vision
Art Historical Research
Automated Attribution
🔎 Similar Papers
No similar papers found.
