Year: 2020
Type: article
Abstract: We tackle the image reassembly problem with wide space between the fragments, in such a way that the patterns and colors continuity is mostly unusable. The spacing emulates the erosion of which the archaeological fragments suffer. We crop-square the fragments borders to compel our algorithm to learn from the content of the fragments. We also complicate the image reassembly by removing fragments and adding pieces from other sources. We use a two-step method to obtain the reassemblies: 1) a neural network predicts the positions of the fragments despite the gaps between them; 2) a graph that leads to the best reassemblies is made from these predictions. In this paper, we notably investigate the effect of branch-cut in the graph of reassemblies. We also provide a comparison with the literature, solve complex images reassemblies, explore at length the dataset, and propose a new metric that suits its specificities.
Institutions: Centre National de la Recherche Scientifique, Université Paris-Seine, Equipes Traitement de l'Information et Systèmes, Université de Cergy-Pontoise, École Nationale Supérieure de l'Électronique et de ses Applications, École nationale des ponts et chaussées, Laboratoire d'Informatique Gaspard-Monge, Université Gustave Eiffel, Université Paris-Saclay, Informatique, BioInformatique, Systèmes Complexes, Université d'Évry Val-d'Essonne
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2998875450