부산대학교 도서관

The width of cut tobacco is a crucial factor that affects the quality and performance of cigarettes. However, conventional methods for measuring tobacco width are time-consuming, labor-intensive, and prone to errors. In this paper, we propose a novel method for online tobacco width detection based on a skeleton detection algorithm. Our method can automatically extract suitable points for width measurement from irregularly shaped and occluded tobacco images, and calculate their widths based on the skeleton slope. We evaluate our method on different tobacco samples with various widths and demonstrate that it can achieve high accuracy and efficiency, as well as real-time monitoring of tobacco width on the production line.