【摘要】 利用机器视觉技术对三七种苗样本进行外观品质分级。采集200株三七种苗的图像并进行预处理,研究了像素点个数与种苗质量之间的关系,建立了线性预测模型,并提取了影响三七外观品质分级的种类、鹰嘴、侧根数的重要特征参数,采用支持向量机建立了三七种苗外观品质分级模型。研究结果表明:种苗质量与像素点个数之间有极显著的线性关系,外观品质检测的识别率在97%以上,表明提出的三七种苗外观综合品质检测方法能较好地实现三七种苗分级。更多还原

【Abstract】 The appearance quality of the samples of Panax notoginseng seedlings was graded by machine vision technology. Images of 200 panax notoginseng seedlings were collected and preprocessed. The relationship between the number of pixels and seedling quality was studied, and a linear prediction model was established. The panax notoginseng seedlings important characteristic parameters, species, olecranon and the number of lateral roots were extracted, and the classification model of appearance quality of panax notoginseng seedlings was established by using support vector machine. The results show that there is a significant linear relationship between seedling quality and the number of pixels; and the recognition rate of appearance quality inspection is over 97%. Explain that the comprehensive quality testing methods for the appearance of Panax notoginseng seedlings proposed in this paper can better achieve the classification of Panax notoginseng seedlings.更多还原