基于几何特征的X射线图像中圆形标志点自动提取

从X射线图像中快速准确地提取圆形标志点是基于C形臂的手术导航中进行跟踪的关键环节。由于在实际应用中X射线图像的标记点半径较小，并且有其他的背景噪声和干扰物，使得一些传统的圆形检测方法往往鲁棒性不够高。针对这一问题，本文提出了一种基于几何特征的圆形目标检测方法，利用这种方法能够对X射线图像中的圆形标记点进行自动提取。实验测试表明该方法能够有效地检测不同半径的圆，并且能够通过调节参数检测到不标准的圆形。实验结果显示该方法在对C形臂X射线成像中的圆形标志物的自动提取具有较高的效率及鲁棒性。

Automatic Circular Marker Detection for X ray Images Base on Geometric Parameter

Automatic detection of markers for fluoroscopic images is the key for fluoroscopy-based navigation system. Due to the small radius of markers and background noises, the robust and the precision of traditional circle detection algorithms are not satisfied. In order to solve this problem, a geometric-parameter based algorithm, which can extract markers automatically from X ray images, is proposed. The method can detect the circles of different radius in fluoroscopic images and non standard circles by adjusting the parameter. The experimental results show that the proposed algorithm holds high efficiency and robustness.