本平台为互联网非涉密平台,严禁处理、传输国家秘密或工作秘密

基于计算机视觉技术的梗丝形态表征方法

  • 摘要: 为研究梗丝形态表征方法,采用图像分析软件对CCD相机获取的梗丝二维图像进行处理,利用拟合方程计算出梗丝的均匀性系数和特征宽度,结合梗丝宽度分布区间建立了梗丝形态的表征方法。结果表明:①用叶丝宽度分布方程对8个梗丝样品宽度拟合,其决定系数R2均超过0.98,且残差均在±0.1以内,适用于梗丝宽度分布的计算。②采用梗丝特征宽度、占比最高的宽度分布区间2项指标表征梗丝形态,将梗丝形态划分为4种,丝状梗丝特征宽度y≤1.2 mm,占比最高的梗丝宽度区间为0.6~1.2 mm;片状梗丝特征宽度y≥1.8 mm,占比最高的梗丝宽度区间为>1.8 mm;近丝状梗丝特征宽度1.2< y<1.8 mm,占比最高的梗丝宽度区间为0.9~1.5 mm;近片状梗丝特征宽度1.2< y<1.8 mm,占比最高的梗丝宽度区间为1.2~1.8 mm。③梗丝均匀性系数大于等于5.5的样品均匀性较好,反之均匀性较差。

     

    Abstract: The 2-Dimensional digital images of cut stems captured by a CCD camera were processed with image analysis software, the uniformity coefficient and characteristic width of cut stems were computed by fitting equation, and the method for morphology characterization of cut stems was developed by combining with the distributing ranges of cut stem width. The results showed that: 1) Fitting the width of 8 cut stem samples with the function representing cut strip width distribution, the determination coefficients (R2) all exceeded 0.98 with residual errors within ±0.1, it indicated that this function also applied to cut stem width. 2) By the characteristic width and the main width range of cut stem, the morphologies of cut stems were divided into 4 types: filamentous cut stem, its characteristic width y was ≤1.2 mm and the main width range (WR) was 0.6-1.2 mm; flake cut stem, y≥1.8 mm and WR>1.8 mm; filament-like cut stem, 1.2 < y <1.8 mm and WR 0.9-1.5 mm; flake-like cut stem, 1.2 < y <1.8 mm and WR 1.2-1.8 mm. 3) When the uniformity coefficient was ≥5.5, the samples had better uniformity.

     

/

返回文章
返回