ChainLineNet: Deep-Learning-Based Segmentation and Parameterization of Chain Lines in Historical Prints
- 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.
Author: | Aline Sindel, Thomas Klinke, Andreas Maier, Vincent Christlein |
---|---|
URN: | urn:nbn:de:hbz:832-epub4-17187 |
DOI: | https://doi.org/10.3390/jimaging7070120 |
ISSN: | 2313-433X |
Parent Title (English): | Journal of Imaging |
Publisher: | MDPI |
Document Type: | Article |
Language: | English |
Date of first Publication: | 2021/07/19 |
Date of Publication (online): | 2021/11/11 |
GND-Keyword: | Deep Learning |
Tag: | Chain Lines; Differentiable Line Fitting; Fourier Transform; Generative Adversarial Networks; Historical Prints; Line Detection; Line Parameterization; Line Segmentation; Paper Structure |
Volume: | 7 |
Issue: | 7 |
Article Number: | 120 |
Page Number: | 17 |
Institutes: | Kulturwissenschaften (F02) / Fakultät 02 / Cologne Institute of Conservation Sciences |
Dewey Decimal Classification: | 500 Naturwissenschaften und Mathematik |
Open Access: | Open Access |
DeepGreen: | DeepGreen |
Licence (German): | ![]() |