Square Puzzle Solving Using Border Compatibility Matching

This paper we proposed a vision-based square puzzle reconstruction method using the color compatibility feature. Using similarity equation via Hausdorff-based border compatibility, the best piece of a puzzle can be obtained to form the initial combination by calculating the similarity of adjacent pieces and completing the puzzles after three combinations. Based on the experimental results tested on 25 images where classified into 35-piece and 70-piece puzzles, the average success rate reached 87.1% and 17 of the 35-piece puzzles were solved with 100% accuracy. For the class of 70 pieces, 77.8% was obtained on average, and 13 of them were solved with 100% accuracy.