基于机器视觉的香梨雌雄自动识别方法  

Automatic Identification of Male and Female Pear Based on Machine Vision

作　　者：李亚硕 祁雁楠 吕程序[1] 毛文华[1] 周丽萍[1] 赵博[1] LI Yashuo;QI Yannan;LV Chengxu;MAO Wenhua;ZHOU Liping;ZHAO Bo(Chinese Academy of Agricultural Mechanization Sciences,Beijing 100083,China)

机构地区：[1]中国农业机械化科学研究院,北京100083

出　　处：《农业工程》2018年第7期61-65,共5页AGRICULTURAL ENGINEERING

基　　金：国家重点研发计划(项目编号:2016YFD0400905)

摘　　要：为实现香梨雌雄的自动识别,利用香梨的花萼特征和外形特征进行分类。通过相机采集香梨图像,对图像进行灰度化、分割、旋转、边缘处理和轮廓提取等预处理,获取花萼处的圆度和香梨长径短径等特征。将获取的特征通过神经网络训练得到分类器模型,用以判断香梨雌雄。所提出的方法能够有效地提取香梨特征,快速识别香梨雌雄,准确率达到92%。In order to realize automatic identification of female and male of fragrant pear,characteristics of calyx and shape of fragrant pear were used for classification.Image of fragrant pear was collected by camera,and image was preprocessed with gray,segmentation,rotation,edge processing,contour extraction and so on.Characteristics of roundness at calyx and short and long axis of fragrant pear were obtained.Classifier model was obtained by neural network training,which was used to judge female and male of fragrant pear.The method could effectively extract characteristics of fragrant pear,and quickly identify male and female of fragrant pear,accuracy rate could be 92%.

关 键 词：香梨 雌雄 花萼 自动识别 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]