摘要
在分析单目定距采集到的鸡蛋图像的各颜色分量直方图的基础上,提出了一种检测鸡蛋外形参数的方法,即针对鸡蛋原始图像的R分量图像,采用最小二乘法的椭圆拟合方法。应用30枚鸡蛋样本分别建立了鸡蛋外形参数长轴、短轴的预测模型,其相关系数分别为0.984 3,0.984 2,定标标准误差分别为0.24,0.12;应用5枚鸡蛋样本验证预测模型,其预测误差分别为0.09,0.05,并通过了F验证,为鸡蛋的机械化加工、分级和生物力学特性研究等奠定了一定的基础。
The ellipse fitting method based on the least squares method to detect the egg appearance parameter is established through R component image of egg original image,based on the analysis of the color component histograms of egg image collected by monocular fixed distance.The prediction models of egg Max-length and Max-width are established through thirty eggs with related coefficient of 0.9843 & 0.9842,and with calibration standard error of 0.24 & 0.12.Then the prediction models with prediction error of 0.09 & 0.05 are verified through five eggs,and also passed the F verification.The research has made a certain theory basis for egg mechanization process,grading and biomechanical characteristics study.
出处
《农机化研究》
北大核心
2012年第5期42-45,共4页
Journal of Agricultural Mechanization Research
基金
天津科学技术委员会星火计划项目(09ZHXHNC06600)
关键词
鸡蛋
最小二乘法
椭圆拟合
外形参数
预测模型
egg
least squares method
ellipse fitting method
appearance parameter
prediction model
