首页 | 本学科首页   官方微博 | 高级检索  
     

葡萄硬枝嫁接苗木愈伤组织融合比例的视觉检测方法
引用本文:袁全春,徐丽明,邢洁洁,段壮壮,马帅,于畅畅. 葡萄硬枝嫁接苗木愈伤组织融合比例的视觉检测方法[J]. 中国农业大学学报, 2018, 23(7): 126-132
作者姓名:袁全春  徐丽明  邢洁洁  段壮壮  马帅  于畅畅
作者单位:中国农业大学工学院
基金项目:现代农业产业技术体系建设专项资金资助(CARS-29)
摘    要:针对葡萄硬枝嫁接苗木愈伤组织融合过程发生在苗木内部,难以检测愈伤组织融合比例的问题,提出一种基于计算机视觉的无损检测方法。采用计算机断层扫描技术(CT)获取葡萄硬枝嫁接苗木嫁接口不同位置处断层图像;通过提取感兴趣区域、添加掩模,简化处理过程;采用最大类间方差阈值分割法将筛管、导管以及嫁接口未融合区域的特征分割出来;采用8邻域区域生长法标记连通域,并设置面积阈值,将嫁接口未融合区域的特征提取出来;采用累计概率霍夫变换直线检测的方法,细化嫁接口未融合区域特征;将嫁接口不同位置处的未融合区域特征叠加,得到总的未融合区域特征;分别计算出总的未融合区域特征面积和嫁接口面积,进而求得融合比例。试验结果表明:该算法的处理时间为92.39s,相对误差3.31%,可以快速并准确地检测出葡萄硬枝嫁接苗木愈伤组织的融合比例。本研究提出的视觉检测方法可以为研究葡萄硬枝嫁接苗木愈伤组织融合过程、融合机理及融合影响因素提供技术支撑。

关 键 词:葡萄硬枝嫁接  愈伤组织融合比例  视觉检测  区域生长  霍夫变换
收稿时间:2017-09-02

Visual inspection method for the callus fusion ratio of grape hard branch grafting seedlings
YUAN Quanchun,XU Liming,XING Jiejie,DUAN Zhuangzhuang,MA Shuai and YU Changchang. Visual inspection method for the callus fusion ratio of grape hard branch grafting seedlings[J]. Journal of China Agricultural University, 2018, 23(7): 126-132
Authors:YUAN Quanchun  XU Liming  XING Jiejie  DUAN Zhuangzhuang  MA Shuai  YU Changchang
Affiliation:College of Engineering, China Agricultural University, Beijing 100083, China,College of Engineering, China Agricultural University, Beijing 100083, China,College of Engineering, China Agricultural University, Beijing 100083, China,College of Engineering, China Agricultural University, Beijing 100083, China,College of Engineering, China Agricultural University, Beijing 100083, China and College of Engineering, China Agricultural University, Beijing 100083, China
Abstract:Aiming at the problem of difficulty in inspecting callus fusion ratio because the fusion process occurs inside the branch,a nondestructive inspecting method based on computer vision was proposed in this study.The computed tomography was used to obtain the tomography images at different positions of the graft union for grape hard grafting seedlings.By extracting regions of interest and adding mask,the processing was simplified.The features of sieve tube,duct,and non fusion area of graft union were separated by adopting the maximum between-cluster variance threshold segmentation method.Eight neighborhood region growing method was used to mark connected domain,area threshold was set and the non fusion area features of the graft union were extracted.And by adopting cumulative probability Hough transformation line detection,the non fusion area features of the graft union were refined.The non fusion area features at different positions of the graft union were added,and the total non fusion area feature was obtained.By calculating the total non fusion feature area and the graft union area respectively,and the callus fusion ratio was then obtained.The results showed:The processing of the algorithm was 92.39 s,and the relative error was 3.31%,the callus fusion ratio of grape hard branch grafting seedlings could be detected quickly and accurately.The visual inspection method of this study provided technical support for the study of process,mechanism and influence factors of the callus fusion of grape hard branch grafting seedlings.
Keywords:grape hard branch grafting  callus fusion ratio  visual inspection  region growing  PPHT
本文献已被 CNKI 等数据库收录!
点击此处可从《中国农业大学学报》浏览原始摘要信息
点击此处可从《中国农业大学学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号