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

Marie-Morgane Paumard 1 David Picard 2 Hedi Tabia 2
2 MIDI
ETIS - Equipes Traitement de l'Information et Systèmes
Abstract : 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.
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01820489
Contributor : Marie-Morgane Paumard <>
Submitted on : Tuesday, December 4, 2018 - 10:23:25 AM
Last modification on : Wednesday, February 20, 2019 - 1:25:09 PM
Long-term archiving on : Tuesday, March 5, 2019 - 1:39:53 PM

File

icip18_paper.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01820489, version 2

Collections

Citation

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⟩

Share

Metrics

Record views

77

Files downloads

226