Multi-Phase Relaxation Labeling for Square Jigsaw Puzzle Solving
This work addresses the challenge of automated puzzle assembly for applications in image processing and computer vision, but it is incremental as it builds on existing relaxation labeling techniques.
The authors tackled the problem of solving square jigsaw puzzles automatically without prior information, using a multi-phase relaxation labeling method that guarantees convergence and includes a new compatibility function, achieving competitive results on standard datasets.
We present a novel method for solving square jigsaw puzzles based on global optimization. The method is fully automatic, assumes no prior information, and can handle puzzles with known or unknown piece orientation. At the core of the optimization process is nonlinear relaxation labeling, a well-founded approach for deducing global solutions from local constraints, but unlike the classical scheme here we propose a multi-phase approach that guarantees convergence to feasible puzzle solutions. Next to the algorithmic novelty, we also present a new compatibility function for the quantification of the affinity between adjacent puzzle pieces. Competitive results and the advantage of the multi-phase approach are demonstrated on standard datasets.