摘要
介绍了分形维数的理论计算公式和试验公式,分析了计盒维数的计算方法,运用Matlab软件设计了图像的处理和基于图像的计盒维数的计算程序。随机地选择了4种双子叶杂草和两种单子叶杂草共6种杂草作为研究对象,运用自行设计的程序分别计算了杂草叶的RGB三色图像的分形维数并以其平均值作为杂草叶的分形维数。研究结果表明该文给出的分形维数的计算方法可靠;研究结果也验证了杂草叶具有分形特征;研究结果还说明不同种类的杂草,其叶的分形维数明显不同,可以用分形维数为特征参数识别杂草。
Theoretical and testing calculation formulas of fraetal dimension were introduced. The calculation method about box-counting dimension based on image processing was analyzed. Program about dimension and image processing based on Matlab were designed. Six weeds （2 of monocotyledon and 4 of dicotyledon） were picked out randomly and fraetal dimensions of the six weed leaves were calculated using the program. Research results show that the calculation method for fraetal dimension presented in this paper is reliable. Research results validate that weed leaf has fraetal feature, and also prove that weed can be discriminated depending on feature parameters of fractal dimension because the fractal dimensions of varieties of weed are different apparently.
出处
《农业工程学报》
EI
CAS
CSCD
北大核心
2006年第11期175-178,共4页
Transactions of the Chinese Society of Agricultural Engineering
基金
江苏省农机局
南京农业大学工学院科研启动基金资助(GXZ05003)
关键词
杂苹识别
图像分析
分形维数
计盒维数
计算方法
weed recognition
image analysis
fractal dimension
box-counting dimension
calculation method
