以平面图形经过欧氏变换后的不变性质定理——相似夹角定理为理论基础， 通过构造一个夹角波动方差函数可用来衡量两条边缘轮廓曲线的相似程度，进而形成了一种图形边缘相似度算法，从而为图形匹配、图形搜索、图形有效相似变换和聚类等提供了一种合理的方法。通过理论论证与实验表明,该方法确能有效反映曲线间的相似程度。

In this paper we bring forward an image edge similitude extent algorithm based on the steadiness character theorem of plane similitude graphics—similitude included angle theorem, and the algorithm is realized by constructing an AFMSDF (mean-square deviation function of angle fluctuation). The AFMSDF is used as a method of scaling the similitude extent of two different edge contours. This algorithm provides a reasonable method for graphic match, graphic search, efficient graphic similitude transform,and clustering, etc. Theoretical analysis and experiments indicate that the method is feasible.