Abstract: Structural analysis is an important step during the recognition process of mathematical expressions.And relationships between symbols is a key of structural analysis.However，the indefinition of the relationships often lead to ambiguity.And it has become difficulty to structural analysis of mathematical expression.This paper extracts visible features，and uses multi-features fuzzy pattern recognition to create subjection function in order to judge the relationship by statistic data.The result shows that this method can be applied in wider scope，its correct-rate is higher，and it is more robust.

摘要： 数学表达式的识别过程中，结构分析是非常重要的一步。而符号关系的判定又是结构分析的关键。然而符号间关系的不确定性导致数学表达式运算含义的模糊性，已经成为数学公式识别中结构分析的一大难点。通过大量的统计数据，抽取出较为明显的特征，并引入多特征模糊模式识别的方法，建立隶属函数来判断印刷体数学公式符号的关系。实验结果表明，该方法适用范围较广，准确率较高，具有较强的鲁棒性。