在预处理阶段，分析纹理样图中特征点的全局分布，并计算样图结构坐标。

In the preprocessing stage, the global distribution of feature points in the sample texture was analyzed and structural coordinates of the sample texture were computed.

youdao

实验结果表明，对于高分辨率的舰船上层结构的红外象而言，局部化特征优于全局化特征，即采用样条函数法比FFT法有较高识别率。

The results indicate that, for high resolution superstructure of IIR of ship targets, lo-cal features are better than global features. That is, spline function method is better than FFT method.

youdao

利用网络社区模块结构作为特征选择的度量指标，给出了一种基于全局拓扑结构的特征选择性能评价方法。

Taking community structure as measurement index for feature selection, a new feature selection measure approach based on modularity coefficient community structure is proposed.

youdao