共焦显微图象如荧光染色细胞核图象，往往是一种比较模糊的图象，并且亮度范围大，灰度均匀度也较差。
In most of cases, the laser scanning confocal microscopy images, such as fluorescence stained biomedical nuclei, are blurred and have a wide range of brightness and poor intensity homogeneity.
本文给出了衡量模糊图连通性的三个度量：模糊连通度、模糊边连通度与模糊核度及其相关的性质。
In this paper, three measure of the connectedness of a fuzzy graph: fuzzy connectivity, fuzzy edge connectivity, fuzzy nuclearity and their properties are presented.
并用正态核加权和密度函数拟合法解决了非正态图象模板匹配的优化问题。
By means of the density function fitting method of weighted sum of normal kernels the optimizing problem of template matching for non-normal distribution image is solved.
通过在ORL，YALE和FERET人脸库上的实验结果表明，提出的具有统计不相关的核化图嵌入算法在识别率方面好于已有的核算法。
The experimental results on ORL, YALE and FERET face databases show that the proposed uncorrelated kernel extension of graph embedding method is better than other methods in terms of recognition rate.
病理染色图象分析测定左室腔周长和面积、单位面积内心肌细胞核数、单位面积内胶原的含量；
Pathological staining and image analysis were used to determine the perimeter and the area of left ventricular cavity, and myocardial nuclei number and collagen content per unit area;
通过红外吸收谱图、核磁谱图和质谱分析与目标产物一致。
Derivatives are the same with target product through IR, 1HNMR, 13CNMR and EI-MS.
另外，揭示了统计不相关的核化图嵌入与已有的核化图嵌入的内在关系。
Besides, the relation between uncorrelated kernel extension of graph embedding and kernel extension of graph embedding is revealed.
提出统计不相关的核化图嵌入算法，为求解各种统计不相关的核化降维算法提供了一种统一方法。
An uncorrelated kernel extension of graph embedding which provides a unified method for computing all kinds of uncorrelated kernel dimensionality reduction algorithms is proposed.
应用图象分析技术测定57例乳腺癌细胞核形态参数，观察它们在不同临床病理状况下与预后的关系。
The prognostic value of morphometric parameters in 57 patients with breast carcinoma of different clinical pathological features was studied.
应用图象分析技术测定57例乳腺癌细胞核形态参数，观察它们在不同临床病理状况下与预后的关系。
The prognostic value of morphometric parameters in 57 patients with breast carcinoma of different clinical pathological features was studied.
应用推荐