【摘要】 传统的部分Ｈａｕｓｄｏｒｆｆ 距离，由于采用固定的分位数，在图像匹配应用中具有相当的局限性。运用非参数和参数统计手段，从模板距离图计算距离变量的经验分布函数，充分挖掘模板中有关像元分布结构的信息，设计出一种稳健的自适应Ｈａｕｓｄｏｒｆｆ 距离计算法。分析表明，新的距离计算式对分位数初值的敏感程度较传统的部分Ｈａｕｓｄｏｒｆｆ 距离小得多，在强噪声和复杂背景下具有很好的抗差性能。更多还原

【Abstract】 The conventional partial Hausdorff distances have strong limitations because of their fixed fractions. In the paper, a kind of robust and adaptive Hausdorff distance with non\|parametric and parametric statistical methods is designed. The new distance makes full use of the information associated with the edge distribution structure of templates, and has less sensitivity of the primary values of the fractions than the conventional distances. It is proved out by algorithmic analysis that the new distance is also keeping excellent performance in matching template in heavily blurred and complex background. \;更多还原