摘要
基于不同的颜色特征,利用机器视觉技术自动识别棉田中铁苋菜。分别对棉花和杂草铁苋菜的色差法(R-G,R-B,G-B)、超绿法(2G-R-B)、色度法(H)等5种特征图像进行对比,确定色度法利用最大方差进行二值化的效果最佳。创建与二值图像相对应的0、1双精度型矩阵,并分别与R、G、B三基色分量图相乘,获取前景是R、G、B三基色分量图,背景是黑色的灰度图像。分析棉花、铁苋菜前景R、G、B的标准差,确定R的标准差与B的标准差差值小于5作为判断铁苋菜的阈值。识别结果表明,棉花的判断准确率为71.4%,铁苋菜的判断准确率为92.9%,总体准确率为82.1%。
Automatic recognition research on distinguishing copperleat herb from cotton was aevelopea by machine vision based on the different color features. The binary images were obtained by segmenting five feature images, which were the color-difference methods （R -G, R -B, G -B）, the supergreen＇ s method （2G - R - B ）, and chromatometry （H） respectively. The chromatometry feature images segmented by Otsu＇s method could achieve better results by comparing. The double precision matrix as 0, 1 was created with the corresponding binary image, and multiplied by the component plans of R, G and B respectively. The gray images were gained. Their foregrounds were the component plans of R, G and B and their backgrounds were black. The standard deviations of R, G and B in the foregrounds of the cotton and the copperleaf herb images were analyzed. The threshold value for the judgment of the copperleaf herb, which was the margin between R＇s standard deviation and B＇s standard deviation less than 5, was determined. The identifiable results show that the recognition rates of the cotton and the copperleaf herb are 71.4% and 92.9% respectively, and the overall recognition rate is 82.1%.
出处
《农业机械学报》
EI
CAS
CSCD
北大核心
2009年第5期149-152,共4页
Transactions of the Chinese Society for Agricultural Machinery
基金
镇江市农业科技计划资助项目(GJ2008008)
江苏大学现代农业装备与技术省部共建教育部重点实验室开放基金资助项目(NZ200708)
江苏省博士后科研资助计划(0601014B)
关键词
棉花
杂草识别
机器视觉
颜色特征
标准差
Cotton, Weed recognition, Machine vision, Color feature, Standard deviation
作者简介
陈树人．教授，博士后，主要从事精确农业研究，E—mail：srchen@ujs．edu.cn
