Sindel A, Maier A, Christlein V (2021)
Publication Language: English
Publication Type: Conference contribution, Conference Contribution
Publication year: 2021
Publisher: IEEE Computer Society
Pages Range: 994-998
Event location: Online ( Anchorage, AK, USA )
ISBN: 978-1-6654-4115-5
DOI: 10.1109/ICIP42928.2021.9506071
Visual light photography, infrared reflectography, ultraviolet fluorescence photography and x-radiography reveal even hidden compositional layers in paintings. To investigate the connections between these images, a multi-modal registration is essential. Due to varying image resolutions, modality dependent image content and depiction styles, registration poses a challenge. Historical paintings usually show crack structures called craquelure in the paint. Since craquelure is visible by all modalities, we extract craquelure features for our multi-modal registration method using a convolutional neural network. We jointly train our keypoint detector and descriptor using multi-task learning. We created a multi-modal dataset of historical paintings with keypoint pair annotations and class labels for craquelure detection and matching. Our method demonstrates the best registration performance on the multi-modal dataset in comparison to competing methods.
APA:
Sindel, A., Maier, A., & Christlein, V. (2021). CraquelureNet: Matching The Crack Structure In Historical Paintings For Multi-Modal Image Registration. In Proceedings of the 2021 IEEE International Conference on Image Processing (ICIP) (pp. 994-998). Online ( Anchorage, AK, USA ): IEEE Computer Society.
MLA:
Sindel, Aline, Andreas Maier, and Vincent Christlein. "CraquelureNet: Matching The Crack Structure In Historical Paintings For Multi-Modal Image Registration." Proceedings of the 2021 IEEE International Conference on Image Processing (ICIP), Online ( Anchorage, AK, USA ) IEEE Computer Society, 2021. 994-998.
BibTeX: Download