Vision-Based Jigsaw Puzzle Solving with a Robotic Arm

This study proposed two algorithms for reconstructing jigsaw puzzles by using a color compatibility feature. Two realistic application cases were examined: one involved using the original image, while the other did not. We also calculated the transformation matrix to obtain the real positions of each puzzle piece and transmitted the positional information to the robotic arm, which then put each puzzle piece in its correct position. The algorithms were tested on 35-piece and 70-piece puzzles, achieving an average success rate of 87.1%. Compared with the human visual system, the proposed methods demonstrated enhanced accuracy when handling more complex textural images.

Automated summary

This study introduces two algorithms to reconstruct jigsaw puzzles using a color compatibility feature. Two realistic application cases were examined, one with the original image and the other without it. The study also involved calculating the transformation matrix to determine the real positions of each puzzle piece and transmitting the positional information to a robotic arm for accurate placement. The algorithms achieved an average success rate of 87.1% when tested on 35-piece and 70-piece puzzles, demonstrating improved accuracy in handling complex textural images compared to the human visual system.