基于机器视觉技术对烟叶部位识别方法的研究

Research on Tobacco Leaf Position Recognition Method Based on Machine Vision Technology

为探究机器视觉技术对烟叶部位的识别,通过对专家分级烟叶样本进行图像采集,提取样本烟叶图像中烟叶的颜色、形态等特征,采用不同的分类方法对训练集进行训练建模,再利用分类模型对测试集进行预测分类。结果表明:提取图像中烟叶的颜色、形态等特征能够较好地区分烟叶部位,采用朴素贝叶斯分类器判别其分类效果最好,准确率可达88.89%。该结果为实际工业分级的机器视觉技术运用提供了理论基础和数据来源。

In order to explore the recognition of tobacco leaf parts by machine vision technology,the color,shape and other characteristics of tobacco leaves in the sample tobacco leaf images were extracted by collecting images of tobacco leaf samples graded by experts,and different classification methods were used to train the training set.The model performs predictive classification on the test set.The results showed that the extracting color and shape of tobacco leaves in the image can better distinguish the parts of tobacco leaves.The Naive Bayesian Classifier is used to determine the best classification effect,and the accuracy rate can reach 88.89%.The results provide a theoretical basis and data source for the application of machine vision technology in practical industrial grading.