TY - JOUR U1 - Zeitschriftenartikel, wissenschaftlich - begutachtet (reviewed) A1 - Sindel, Aline A1 - Klinke, Thomas A1 - Maier, Andreas A1 - Christlein, Vincent T1 - ChainLineNet: Deep-Learning-Based Segmentation and Parameterization of Chain Lines in Historical Prints JF - Journal of Imaging N2 - The paper structure of historical prints is sort of a unique fingerprint. Paper with the same origin shows similar chain line distances. As the manual measurement of chain line distances is time consuming, the automatic detection of chain lines is beneficial. We propose an end-to-end trainable deep learning method for segmentation and parameterization of chain lines in transmitted light images of German prints from the 16th Century. We trained a conditional generative adversarial network with a multitask loss for line segmentation and line parameterization. We formulated a fully differentiable pipeline for line coordinates’ estimation that consists of line segmentation, horizontal line alignment, and 2D Fourier filtering of line segments, line region proposals, and differentiable line fitting. We created a dataset of high-resolution transmitted light images of historical prints with manual line coordinate annotations. Our method shows superior qualitative and quantitative chain line detection results with high accuracy and reliability on our historical dataset in comparison to competing methods. Further, we demonstrated that our method achieves a low error of less than 0.7 mm in comparison to manually measured chain line distances. KW - Deep Learning KW - Line Segmentation KW - Line Detection KW - Line Parameterization KW - Generative Adversarial Networks KW - Fourier Transform KW - Differentiable Line Fitting KW - Chain Lines KW - Paper Structure KW - Historical Prints Y1 - 2021 UN - https://nbn-resolving.org/urn:nbn:de:hbz:832-epub4-17187 SN - 2313-433X SS - 2313-433X U6 - https://doi.org/10.3390/jimaging7070120 DO - https://doi.org/10.3390/jimaging7070120 VL - 7 IS - 7 SP - 17 S1 - 17 PB - MDPI ER -