Autor(en)
Paumard, Marie-Morgane; Picard, David; Tabia, Hedi
Titel
Deepzzle: Solving Visual Jigsaw Puzzles With Deep Learning and Shortest Path Optimization
Teil von
  • IEEE transactions on image processing, 2020, Vol.29, p.3569-3581
Ort / Verlag
PISCATAWAY: IEEE
Links zum Volltext
Quelle
IEEE Electronic Library (IEL) Journals
Beschreibungen
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.

Weiterführende Literatur

Empfehlungen zum selben Thema automatisch vorgeschlagen von bX
Die Universität der Informationsgesellschaft