逆向工程中特征曲面的识别方法

提出了基于二次曲面拟合误差分析和几何属性分析的特征曲面识别算法。首先用一般二次曲面方程拟合测量数据并计算曲面的拟合误差，比较拟合误差与阈值的大小来识别自由曲面和一般二次曲面。然后计算测量点几何属并将它映射到高斯球和法曲率坐标上，运用统计方法识别不同分布模式，从而识别不同的特殊二次曲面类型。为了提高算法的效率和实用性，在计算测量点到拟合曲面的距离时，用近似距离代替精确的欧几里得距离。在识别特殊二次曲面时，优先识别平面。实例表明，该算法能有效识别自由曲面、平面、球面、柱面、锥面和过渡曲面等特征曲面。

Feature surface recognition in reverse engineering

An algorithm of feature surface recognition based on quadric surface fitting and geometry property was presented. Firstly, using quadric surface to fit with given surface and calculate the error metric to identify free surface and general quadric surface. Then, compute geometry property of each point on Gaussian sphere and curvature coordinate. The distribution would identify each kind of quadric surface and blend surface. In order to improve the efficiency and practicability, this algorithm calculated approximation distance from point to surface and make priority to identify planes. This algorithm is easy to recognize plane, cylinder, cone, sphere, blend surface and free surface.