In this article, a low-cost but high-fidelity rolling tactile system is proposed for distinguishing patterns on curved surface, including an improved vision-based tactile sensor (VBTS) and a novel lightweight processing framework. The proposed VBTS contains a modular ring-shaped illumination configuration and an improved sensing elastomer, which is easy to fabricate without complex processing and costs only 16.95 USD in total. To achieve real-time data processing of rolling tactile images, inspired by event-based cameras, an efficient processing framework is introduced based on computer graphics, which can integrate sparse rolling tactile images into complete high-fidelity images for the final classification. To evaluate the effectiveness of the proposed system, a classification model is trained using dataset generated by 13 cylinders with similar textures, where the identification accuracy of validation is up to 98.3%. Then, we test each cylinder sample for 3 rolling tactile perceptions and achieve 100% identification accuracy within 1.2 s on average, indicating a promising prospect of the proposed perception system for real-time application