Abstract
The accurate detection of cracks in paintings, which generally portray rich and varying content, is a challenging task. Traditional crack detection methods are often lacking on recent acquisitions of paintings as they are poorly adapted to high-resolutions and do not make use of the other imaging modalities often at hand. Furthermore, many paintings portray a complex or cluttered composition, significantly complicating a precise detection of cracks when using only photographic material. In this paper, we propose a fast crack detection algorithm based on deep convolutional neural networks (CNN) that is capable of combining several imaging modalities, such as regular photographs, infrared photography and X-Ray images. Moreover, we propose an efficient solution to improve the CNN-based localization of the actual crack boundaries and extend the CNN architecture such that areas where it makes little sense to run expensive learning models are ignored. This allows us to process large resolution scans of paintings more efficiently. The proposed on-line method is capable of continuously learning from newly acquired visual data, thus further improving classification results as more data becomes available. A case study on multimodal acquisitions of the Ghent Altarpiece, taken during the currently ongoing conservation-restoration treatment, shows improvements over the state-of-the-art in crack detection methods and demonstrates the potential of our proposed method in assisting art conservators.
Highlights
Paint cracking is the most common type of deterioration encountered in old master paintings
We are not aware of any reported works that apply convolutional neural networks (CNN) or other deep learning models to the problem of crack detection in paintings, except for our preliminary result in a conference abstract [18]. (ii) We propose a novel method for reducing excessive thickening of the crack boundaries detected by CNNs
We compared our more precise boundary detection (MCNC) method with its reduced version without the improved crack boundary localization – MCN, and against approaches using fully connected neural networks (NN) [50], Boosting methods (ADA) [51], support vector machines (SVM) [52], and the Bayesian Conditional Tensor Factorization method (BCTF) [8]
Summary
Paint cracking (or craquelure) is the most common type of deterioration encountered in old master paintings. Cracks appear in paint layers as a consequence of stress caused by different factors, including the ageing of the materials used (age cracks), a defective technical execution at the painting stage (premature cracks), and adverse storing conditions [1]. The main cause for cracking in 15th century Flemish paintings lies in the fluctuation of relative humidity, causing the. Cracking often occurs in the top varnish layer due to oxidation. The automatic detection of cracks proved to be a considerable help in various art analysis tasks. In [2], [3] crack detection was used in combination with inpainting methods, to digitally remove cracks in selected areas of the Ghent Altarpiece.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
