The generalized Radon transform: Sampling, accuracy and memory considerations
The generalized Radon transform: Sampling, accuracy and memory considerations
复制标题
DOI：
10.1016/j.patcog.2005.04.018
复制
发表时间：
2005-12-01
影响因子：
8
通讯作者：
van Vliet, LJ
中科院分区：
文献类型：
--
作者：
Luengo Hendriks, CL;van Ginkel, M;van Vliet, LJ
广义Radon（或Hough）变换是用于检测图像中的参数化形状的公知工具。Radon变换是图像空间和参数空间之间的映射。后者中的点的坐标对应于图像中的形状的参数。该点的振幅对应于该形状的证据量。在本文中，我们讨论了三个重要方面的Radon变换。第一个方面是离散化。利用采样理论的概念，我们推导出一组广义Radon变换的采样准则。第二个方面是准确性。对于特定的情况下，拉冬变换的领域，我们研究如何以及最大值的位置匹配的真实参数。我们推导出一个校正项，以减少估计半径的偏差。第三个方面是提出了一种基于投影的算法来减少内存需求。(c)2005模式识别学会。由爱思唯尔有限公司出版。保留所有权利。
The generalized Radon (or Hough) transform is a well-known tool for detecting parameterized shapes in an image. The Radon transform is a mapping between the image space and a parameter space. The coordinates of a point in the latter correspond to the parameters of a shape in the image. The amplitude at that point corresponds to the amount of evidence for that shape. In this paper we discuss three important aspects of the Radon transform. The first aspect is discretization. Using concepts from sampling theory we derive a set of sampling criteria for the generalized Radon transform. The second aspect is accuracy. For the specific case of the Radon transform for spheres, we examine how well the location of the maxima matches the true parameters. We derive a correction term to reduce the bias in the estimated radii. The third aspect concents a projection-based algorithm to reduce memory requirements. (c) 2005 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.