Object centroid as the features was computed by means of regional statistics, parameter recognition, noise region removal and cluster analysis.

然后采用区域统计、参数识别、噪声区域去除以及聚类分析等手段进行目标特征识别，提取出棒材的质心点坐标作为特征；

youdao

Parameter study of Bayesian network is investigated. According to the methods of example statistics and correlation analysis, Bayesian diagnosis model of body deviation is established.

对贝叶斯网络的参数学习进行了探讨，结合实例统计和相关性分析建立了车身偏差诊断的贝叶斯网络模型。

youdao