Abstract: A new multidimensional distance vector (MDV) is defined based on corners of airplane outline, each airplane has its MDV different from others. By computing the correlation coefficients of their MDV and comparing correlation between two MDV, each kind of airplane can be recognized from airplane model library. Experiments show that the new MDV is stabile and distinct, the algorithm with high recognition rate is very quick, and almost real time.

Key words: Corner, Multidimensional distance vector (MDV), Correlation coefficient, Pattern recognition

摘要： 根据飞机形状角点之间的距离，定义了一种新的多维距离特征向量，不同飞机具有不同的多维距离向量。计算多维距离特征向量之间的相关系数，比较多维距离特征向量之间的相关性，能将每种飞机从飞机模型库中识别出来。实验表明，这种新特征向量具有较好的稳定性和区分性，算法识别率高、速度快，几乎达到实时效果。

关键词: 角点, 多维距离向量, 相关系数, 模式识别

CLC Number: 

• TP391