基于图像处理的烟叶分拣系统的设计与实现

Study on Inspection of Tobacco Leaves Based on Image Processing

文中介绍的烟叶在线分拣方法是利用数字图像处理及模式识别技术实现的,简要说明了烟叶实时光电分拣系统的原理和结构, 同时,着重讨论了烟叶杂质识别算法,详尽地阐述了利用阈值选取来建立合格烟叶颜色表以及目标杂质的区域标记与确定开阀位置的方法,此分拣设备的应用表明了算法的实时性好,可靠性高,能很好地满足工业生产要求,大大提高了烟叶剔除杂质的自动化与智能化。

The method of online inspection of tobacco leaves is designed on the basis of digital image processing and pattern recognition, The principle and structure of the real--time optical eleclrical inspection of tobacco leaves （ROEITL） is illuminated in brief, At the same time, the inspection algorithm of tobacco leaves is also emphasized on. The method of building the color sheet of eligible tobacco leaves through the threshold value selection and marking the region of target impurities is expounded, as well as locating the middle of the impurities above which gas valves are turned on. The application of the ROEITL shows that its algorithm is real--time and reliable. It also can meet the need of the industrial production well, and enhance the automatization and intelligentization of impurity removing from tobacco leaves greatly.