【作者】 王丽萍； 张彩明；

【Author】 Wang Liping~1 Zhang Caiming~2 (1.School of Computer Science and Technology,Shandong University) (2.School of Computer Science and Technology,Shandong economic University)

【机构】 山东大学计算机科学与技术学院； 山东经济学院计算机科学与技术学院；

【摘要】 三维数据的曲面拟合是模式识别和计算机视觉中的基本问题。现在提出的大多数的曲面拟合的方法是基于最小二乘的,但当数据中存在一定程度的误差或只是从小区域内采样的时,很少能产生满意的结果。本文提出了一个新方法,通过最小化垂直距离的平方和,并用牛顿迭代法使之线性化。这个方法通常会产生好的拟合,实验结果显示算法是可靠有效的。更多还原

【Abstract】 Fining surfaces to 3-D data is one of the basic methods for pattern recognition and compute vision.Most techniques of surface fitting proposed before are “least-squares”-based that rarely produce satisfactory results if a certain level of noise is present in the data or if the data points are locally sampled from a small area.This paper propose a new approach that minimizes the mean squared orthogonal distances with linearization using the Newton iteration method.This approach usually yields a good fit and the algorithm is reliable and efficient.The results demonstrate that the orthogonal distance performs better.更多还原