Towards Automated Detection of Bookbinding Tool Impressions: A Pilot Study

Abstract

This research presents a pilot study on the automated recog-nition of historical bookbinding tools using deep learning and synthetic image generation. The work focuses on the documented collection of Czech binder Jenda Rajman (1892–1965), whose complete set of metal stamping tools provides an ideal reference dataset. Each tool leaves a characteristic impression on leather bindings, forming a unique visual signature that can support attribution, documentation, and conservation of historical works. To address the lack of complete photographic docu-mentation, two complementary synthetic data generation pipelines were developed: the Procedural Compositional Synthesis and the Background-Normalized Synthetic Stamping methods. These pipelines produce large, annotated image sets that simulate realistic embossing under diverse surface and lighting conditions. A YOLO-based deep learning architec-ture (YOLO11 family) was trained and evaluated on datasets generated by both pipelines and their combination. Experimental results indicate that the proposed approach provides a promising direction for further research, demonstrating the feasibility of detecting and classifying small, low-contrast blind-stamped motifs and highlighting the potential of syn-thetic data and deep learning for digital analysis of bookbinding heritage.