Abstract: To address the issues of strong subjectivity, high labor intensity, and limited detection methods in traditional manual analysis of filler parameters and morphological identification within tobacco stems, a novel approach based on computed tomography (CT) imaging technology is proposed for detecting the morphology and parameters of tobacco stem fillers. By employing filter-based reverse projection for three-dimensional reconstruction, combined with gray-level threshold segmentation and connected component analysis, parameters such as length, volume, and quantity of the filter in cigarettes are measured to achieve efficient filter identification and parameter analysis. Results indicate: 1) For Q-brand cigarette detection, CT imaging achieved RSD < 1.00% for filter length measurements with an average relative error of 0.146 mm, and RSD < 5.00% for spatial position detection, demonstrating high precision and excellent repeatability. 2) For P, L, and Y brand cigarettes, the accuracy rate for both filter tip quantity and morphology identification reached 100%, demonstrating excellent repeatability and consistency. This study provides a novel non-destructive testing technique for filter tip morphology identification and parameter analysis in tobacco stems.