化学结构图中化学键信息的自动提取

在化学结构图中,拐点信息异常重要,如果能对化学结构的拐点进行有效的判别,就可使化学键信息提取的有效性得到很大改善。本研究通过对化学结构的图形分析及特征总结,权衡了Hough变换等提取方法的优势和不足,发现了结构图边缘点偏移值的变化具有很强的规律性,其对图形拐点的提取以及化学键键型的判断有着重要作用。基于以上分析,提出了利用化学结构图偏移值变化的规律性进行化学键信息提取的方法。为了论证算法的有效性,实验时选取了100幅化学结构图,对100幅图形的化学键信息进行了提取并进行了统计分析,得出化学键信息的正确提取率为7383％,从而通过实验数据证实了算法的可行性。

The automatic extraction of the chemical bonds information in the chemical structure images

The inflection points are very important for chemical structure graphs. If the inflection points of chemical structures could be discriminant effectively, they would make the effectiveness of the extraction of chemical bond information improved greatly. The characteristics of the chemical structure was analyzed and summarized, and the advantages and disadvantages of the Hough method was balanced. It was found that the offset value of the edge points was with strong regularity,which played an important role on the extraction of the inflection points and the judgment of chemical bond type. Finally, the experiments selected 100 BMP figures of the molecular structure to extract and count the chemical bond information. The statistic results showed that the accuracy rate of chemical bonds information extraction was of 7383％， which proved the effectiveness of this method.