A Rapid Image Comparison Approach to Automatic Recognition and Assembly of Jigsaw Puzzles

Abstract

This paper proposes a method for quick recognition of jigsaw puzzles using a small number of samples, solely relying on image processing and template matching techniques. In the preliminary stage, this paper proposes a segmentation approach to divide the jigsaw puzzle into individual pieces with partial features, obtaining template data for each puzzle piece. Subsequently, scattered puzzle pieces are captured using a camera, and their contours are extracted to acquire puzzle image data. The puzzle images are then matched with the template data, employing polar coordinate transformation during the matching process to reduce computational time. The matching process also identifies the puzzle piece's number and orientation. Finally, the matching results are integrated with a robotic arm to complete the task of puzzle assembly. This paper not only outlines the generation of puzzle image data and template data through image processing but also elaborates on the determination of corresponding numbers and orientations during image matching. The feasibility of this method is validated through different types of puzzles, and its applicability to industrial parts is also examined for practicality.