Lego Parts Recognition Based on Its Unique Characteristics

In this paper, we present a novel approach for recognizing Lego parts, which plays a critical role in automated assembly and sorting systems. Each Lego part possesses unique characteristics, notably the presence of circles on its surface, where the number of circles typically corresponds to the size of the Legs part. By analyzing the arrangement of these circles, we can determine the shape of a Lego part. Our approach focuses on two key aspects: the count of circles and the connectivity of straight lines passing through the circle centers. By carefully examining how these straight lines intersect, we achieve accurate identification of Lego part shapes. To realize Lego parts recognition, we employ computer vision techniques and algorithmic analysis. Initially, we detect and extract circles from images of Lego parts using the Hough transform. Subsequently, we analyze the circle count and plot straight lines through the circle centers. By considering the intersection patterns of these lines, we effectively classify Lego parts into various shapes, including squares, rectangles, triangles, and more complex configurations. Our methodology is validated through extensive experimentation on a substantial dataset of Lego parts. The results demonstrate the effectiveness of our approach, achieving a high accuracy rate of 114 out of 120 successfully recognized Lego part shapes, with minimal false positives and negatives. These quantitative findings underscore the robustness and reliability of our method. In conclusion, our proposed approach offers a promising solution for automating Lego part recognition in assembly and sorting systems, leading to improved efficiency and productivity. The significant findings from our research contribute to advancing the field of Lego parts recognition and hold potential for various practical applications.