Genetic Algorithm-Based Solver for Very Large Multiple Jigsaw Puzzles of Unknown Dimensions and Piece Orientation
Computer Vision and Pattern Recognition
2017-11-21 v1 Neural and Evolutionary Computing
Abstract
In this paper we propose the first genetic algorithm (GA)-based solver for jigsaw puzzles of unknown puzzle dimensions and unknown piece location and orientation. Our solver uses a novel crossover technique, and sets a new state-of-the-art in terms of the puzzle sizes solved and the accuracy obtained. The results are significantly improved, even when compared to previous solvers assuming known puzzle dimensions. Moreover, the solver successfully contends with a mixed bag of multiple puzzle pieces, assembling simultaneously all puzzles.
Keywords
Cite
@article{arxiv.1711.06766,
title = {Genetic Algorithm-Based Solver for Very Large Multiple Jigsaw Puzzles of Unknown Dimensions and Piece Orientation},
author = {Dror Sholomon and Eli David and Nathan S. Netanyahu},
journal= {arXiv preprint arXiv:1711.06766},
year = {2017}
}