Generating Jigsaw Puzzles and an AI Powered Solver.

This paper tackles the problem of assembling a jigsaw puzzle, starting only from a picture of the scrambled jigsaw puzzle pieces on a random, textured background. This manuscript discusses previous approaches in dealing with the jigsaw puzzle problem and brings two contributions: an open source tool for creating realistic scrambled jigsaw puzzles meant to serve as a foundation for further research in the field; and an end to end AI based solution taking advantage of the convolutional neural network architecture, capable of solving a scrambled jigsaw puzzle of unknown pictorial and with an unknown, uniformly textured, background. The lessons and techniques learned in engaging with the jigsaw puzzle problem can be further used in approaching the more general and complex problem of Protein-Protein interaction prediction.