Craquelure as a Graph: Application of Image Processing and Graph Neural Networks to the Description of Fracture Patterns

TL;DR

This paper introduces a novel graph-based methodology for analyzing craquelure patterns in paintings, leveraging graph neural networks and statistical features to improve origin classification accuracy.

Contribution

The work develops a new graph representation of craquelure patterns and combines graph neural networks with handcrafted features for enhanced artwork analysis.

Findings

Outperforms existing techniques in origin classification

Graph representation captures network structure invariant to distortions

Combining GNN and handcrafted features yields best results

Abstract

Cracks on a painting is not a defect but an inimitable signature of an artwork which can be used for origin examination, aging monitoring, damage identification, and even forgery detection. This work presents the development of a new methodology and corresponding toolbox for the extraction and characterization of information from an image of a craquelure pattern. The proposed approach processes craquelure network as a graph. The graph representation captures the network structure via mutual organization of junctions and fractures. Furthermore, it is invariant to any geometrical distortions. At the same time, our tool extracts the properties of each node and edge individually, which allows to characterize the pattern statistically. We illustrate benefits from the graph representation and statistical features individually using novel Graph Neural Network and hand-crafted descriptors correspondingly. However, we also show that the best performance is achieved when both techniques are merged into one framework. We perform experiments on the dataset for paintings' origin classification and demonstrate that our approach outperforms existing techniques by a large margin.