本文提出了一种基于灰度曲面匹配的人耳识别方法。
An ear recognition method based on gray surface matching has been proposed.
用最小二乘法建立曲面匹配的目标函数，并用遗传算法进行求解。
The matching function was built by the Least Squares method, and it was solved by the genetic algorithms.
采用曲线曲面匹配和误差分离技术对测量数据进行处理，完成了对被测件的评价。
The part is evaluated using the techniques such as curve matching, curved face matching and error separating.
在此基础之上，利用改进的迭代算法完成曲面匹配的精确调整达到了全局最优化的目标。
On basis of these, an improved iterative algorithm is used in the exact adjustment to ensure the global optimization.
通过对基准图相关曲面特征与匹配性能参数之间的关系分析，建立了一种综合的评价准则，对不同的特征进行综合的评价。
Analyzing the relationship between the feature of reference-image correlation plane and matching capability, a synthetic rule is established to evaluate different feature.
针对复杂曲面类零件加工余量分析过程中的测量数据匹配问题，提出通过初始匹配和精确匹配来实现曲面测量数据的最佳匹配。
An optimization method was presented for best-fitting of measurement point cloud to the complex surfaces, which consists of rough matching and accurate matching.
交互式的初始匹配过程决定后续算法的变量范围，精确匹配确定测量数据与曲面的最佳匹配姿态。
The rough matching decided the variable range of the follow-up algorithms, whereupon the accurate matching acquird the optimal location.
该算法构造曲面的有向深度图像，将问题由3维转化到2维，通过图像的比较来获得曲面的匹配误差。
By constructing the oriented depth images for each surface, a problem in 3d is transformed into a 2d problem.
该算法构造曲面的有向深度图像，将问题由3维转化到2维，通过图像的比较来获得曲面的匹配误差。
By constructing the oriented depth images for each surface, a problem in 3d is transformed into a 2d problem.
应用推荐