结果表明：该方法提取的缺陷回波信号特征值，其可分性测度均值达91.7%，从而证明该方法对超声检测缺陷回波信号的特征提取是相当有效的。

The average value of separability measure is as high as 91.7%, which indicates that this method is quite effective in the feature extraction of ultrasonic flaw echoes.

youdao

特征空间、几何变换、相似性测度以及优化算法是设计医学图象配准方法时要考虑的四个主要因素。

Many investigator explore in the domain. Medical images registration methods have four main factors: features space, geometry transformation, similarity, and optimizing algorithm.

youdao

区别联合类型特征的维度包括测度产出的成本、监督生产的成本以及生产者之间的产出相关性。

The characteristic dimensions that distinguish the union types include the cost of measuring output, the cost of supervising production and the relativity of production among producers.

youdao