Jigsaw Puzzle Solving Using Local Feature Co-occurrences In Deep Neural Networks - ETIS, équipe MIDI Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Jigsaw Puzzle Solving Using Local Feature Co-occurrences In Deep Neural Networks

Résumé

Archaeologists are in dire need of automated object reconstruction methods. Fragments reassembly is close to puzzle problems, which may be solved by computer vision algorithms. As they are often beaten on most image related tasks by deep learning algorithms, we study a classification method that can solve jigsaw puzzles. In this paper, we focus on classifying the relative position: given a couple of fragments, we compute their local relation (e.g. on top). We propose several enhancements over the state of the art in this domain, which is outperformed by our method by 25%. We propose an original dataset composed of pictures from the Metropolitan Museum of Art. We propose a greedy reconstruction method based on the predicted relative positions.
Fichier principal
Vignette du fichier
icip18_paper.pdf (598.52 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01820489 , version 1 (21-06-2018)
hal-01820489 , version 2 (04-12-2018)

Identifiants

  • HAL Id : hal-01820489 , version 2

Citer

Marie-Morgane Paumard, David Picard, Hedi Tabia. Jigsaw Puzzle Solving Using Local Feature Co-occurrences In Deep Neural Networks. International Conference on Image Processing, Oct 2018, Athens, Greece. ⟨hal-01820489v2⟩
259 Consultations
660 Téléchargements

Partager

Gmail Facebook X LinkedIn More