中文说明：
本文讨论了从平面多边形的复矩量中恢复其顶点的问题。因为给定的、测量的矩可能是噪声的，所以恢复的顶点只是真实顶点的估计。文献中提供了许多算法来解决这种估计问题。我们将仅讨论总体最小二乘（TLS）数据拟合模型HTLS和STL以及矩阵铅笔法GPOF。我们展示了HTLS和GPOF方法之间的密切联系。我们使用HTLS方法来计算STL方法的起始值。我们在模拟数据上比较了这三种方法的准确性。2005爱思唯尔B.V.版权所有。
English Description：
In this paper, the problem of recovering the vertices of a planar polygon from its complex moments is discussed. Because the given and measured moments may be noisy, the recovered vertices are only estimates of the real vertices. Many algorithms are provided in the literature to solve this estimation problem. We will only discuss the total least squares (TLS) data fitting models htls and STL and the matrix pencil method GPOF. We show the close relationship between htls and GPOF methods. We use htls method to calculate the starting value of STL method. We compare the accuracy of these three methods on simulated data. 2005 Elsevier B.V. all rights reserved