Crack Detection in Single- and Multi-Light Images of Painted Surfaces using Convolutional Neural Networks

Cracks represent an imminent danger for painted surfaces that needs to be alerted before degenerating into more severe aging effects, such as color loss. Automatic detection of cracks from painted surfaces' images would be therefore extremely useful for art conservators; however, classical image processing solutions are not effective to detect them, distinguish them from other lines or surface characteristics. A possible solution to improve the quality of crack detection exploits Multi-Light Image Collections (MLIC), that are often acquired in the Cultural Heritage domain thanks to the diffusion of the Reflectance Transformation Imaging (RTI) technique, allowing a low cost and rich digitization of artworks' surfaces. In this paper, we propose a pipeline for the detection of crack on egg-tempera paintings from multi-light image acquisitions and that can be used as well on single images. The method is based on single or multi-light edge detection and on a custom Convolutional Neural Network able to classify image patches around edge points as crack or non-crack, trained on RTI data. The pipeline is able to classify regions with cracks with good accuracy when applied on MLIC. Used on single images, it can give still reasonable results. The analysis of the performances for different lighting directions also reveals optimal lighting directions.

@InProceedings{DGPCJG19,
  author       = {Dulecha, T. and Giachetti, A. and Pintus, R. and Ciortan, I. and Jaspe Villanueva, A. and Gobbetti, E.},
  title        = {Crack Detection in Single- and Multi-Light Images of Painted Surfaces using Convolutional Neural Networks},
  booktitle    = {The 16th Eurographics Workshop on Graphics and Cultural Heritage},
  pages        = {43--50},
  month        = {november},
  year         = {2019},
  keywords     = {Crack Detection, Multi-Light Image Collections (MLIC), Reflectance Transformation Imaging (RTI), Convolutional Neural Network},
  doi          = {10.2312/gch.20191347},
  url          = {https://publications.crs4.it/pubdocs/2019/DGPCJG19},
}