一种基于方向SUSAN特征的目标特征列表匹配

Feature list object matching based on oriented SUSAN features

目标匹配识别中,特征列表相关算法可以有效减少计算时间,匹配具有较高的峰值系数和峰值信噪比,清晰识别目标。提出一种基于方向最小核值相似区(SUSAN)特征列表的目标匹配方法,考虑特征点的方向信息,应用SUSAN原理提取特征并列表描述图像,匹配相似测量基于特征点归一化误差均值,有效降低了算法的噪声敏感性。

For the machine vision object matching, the feature list correlation algorithm can be adopted in the calculation of the matching similarity measurement. As a result, the processing time is able to be decreased considerably, and the objects can also be clearly recognized due to the high values of the coefficients and the high values of the Peak Signal-to-Noise Ratio （PSNR）. A feature list object matching method based on the oriented Smallest Univalue Segment Assimilating Nucleus （SUSAN） features was proposed. The feature pixels with oriented SUSAN features were added to the feature lists and the similarity was based on the normalized absolute error of feature pixelpoints. The supposed algorithm is verified by the experiments.