摘要
评价通过机器视觉的方法进行穗行数自动检测的可行性,提出一种基于边界标记和离散曲率的边缘算法确定行数,建立了检测模型。在扫描78幅不同玉米品种的果穗横断面图像的基础上进行检验。结果表明:试样玉米的穗行数为12～18行,检测的绝对误差为0.103行,相对误差率为0.66%,零误差率达到90%以上。实验证明检测算法真实可靠,机器视觉具有成本和速度上的优势,能够用于玉米穗行数的自动检测。
In order to exam feasibility of ear rows counting method by machine vision,a new method was raised.This method was based on edge marker and discrete curvature.78 digital images of 4 maize cultivars were scanned from 2 sides if maize fragment face.Based on this,it was found that the number was mostly 12-18,and the detecting absolute error was 0.103 and relative error rate was 0.66%.The accuracy rate was above 90%.Machine vision won the advantages of lowcost and high speed over manual or biochemical detecting...
出处
《玉米科学》
CAS
CSCD
北大核心
2010年第2期146-148,152,共4页
Journal of Maize Sciences
基金
山东省科技攻关项目(072137,082115)
山东省科技攻关计划“玉米果穗和子粒的图像处理技术研究与自动分析软件研制”(2009GG10009005)
关键词
玉米
图像处理
边界标记
离散曲率
穗行数
Maize
Image process
Edge marker
Discrete curvature
Number of kernel rows
