一种基于模糊矩阵的空间面对象相似性度量算法

Similarity Measurement Algorithm of Space Face Image Based on Fuzzy Matrix

针对地理信息科学中相似性描述尚未考虑其模糊性本质这一现状,将空间面对象相似性度量进行程度划分,而不是界定在相似和不相似两个绝对地带,从而将空间面对象的相似性度量转化为相似程度评判。以纵横轴比、矩形度、面积凹凸比、周长凹凸比和方向为相似程度评判因子,通过模糊矩阵组建评判矩阵,将空间面对象相似性度量模拟为专家评判系统,最终获取待比较的空间面对象之间的相似程度。通过实例验证,算法具有一定可行性,为相关空间查询、空间分析、空间推理、制图综合、地图匹配等起到一定参考作用。

According to the geographic information science has a certain similarity in the fuzzy nature of space will face as similarity measure degree of division,but not defined in the similar and dissimilar two absolute areas,which will face as the similarity metric space into similarity evaluation.In the axial ratio,rectangularity,bump,bump area than perimeter ratio and direction for the similarity evaluation factors,using fuzzy matrix form evaluation matrix,spatial similarity measure for face simulation expert evaluation system,finally get to compare the spatial similarity between the face image.The example proves that the algorithm is feasible,and it can be used as a reference for spatial query,spatial analysis,spatial reasoning,cartographic generalization and map matching.