摘要
以鸭梨为对象,采用核磁共振成像设备扫描获得轻微损伤鸭梨冠状面图像,使用Matlab软件完成图像预处理,采用自动阈值分割目标区域,并提取鸭梨层切面边界,最后采用角点检测方法检测鸭梨是否有轻微损伤。实验结果表明,核磁共振成像技术对水果轻微损伤的检测精度达92.1%,对正常和畸形水果的检测精度达100%。
The nuclear magnetic resonance（NMR） imaging was proposed to detect the subtle bruises on fruits. Chinese pears were selected as the experimental object. The nuclear magnetic resonance images of pears were acquired by horizontal scanning mode. Image processing,which included auto thresh segmentation,morphologic operation and boundary extraction was finished by Matlab software. At last the corner detection was used to determine whether the pear had subtle bruises. Experimental results showed that detecting subtle bruises on fruits with NMR technique was feasible. The accuracy of detection for subtle bruises and other pears was 92.1% and 100%,respectively.
出处
《农业机械学报》
EI
CAS
CSCD
北大核心
2010年第8期107-110,共4页
Transactions of the Chinese Society for Agricultural Machinery
基金
国家自然科学基金资助项目(30825027)
2010年院级项目
关键词
鸭梨
核磁共振成像
无损检测
角点检测
Chinese pear
Nuclear magnetic resonance imaging
Noninvasive inspection
Corner detection
作者简介
周水琴，博士生，杭州职业技术学院讲师，主要从事农产品无损检测技术研究。E-mail：yingbai18@163．com
通讯作者：应义斌，教授，博士生导师，主要从事农产品无损检测技术研究，E-mail：ybying@zju．edu．cn
