摘要
本文提出一种采用基于勒让特矩(Legendre Moments)的双平面X线血管造影图像血管截面重建的新方法,该方法根据图像的矩与图像本身的唯一性对应的基本原理,应用奇异值分解方法来估计截面的几何矩.在此基础上,计算其勒让特矩,并通过迭代运算最终实现血管截面的重建.这种方法无需先验模型,对截面形状也没有限制.实验结果验证了上述算法的有效性,取得了较满意的结果.
In this paper, a new method is described for reconstructing the cross sections of arteries from X-ray angiog-raphy images based on Legendre moment, which are orthogonal moments. Singular value decomposition is used to estimate the missing moments. Once all missing moments are estimated, the image of the slice can be estimated by using the uniqueness theorem governing the relation between an image and its moments. Experimental results show that the proposed algorithm is efficient and practical.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2002年第1期98-102,共5页
Pattern Recognition and Artificial Intelligence
关键词
X线
血管造影
图像血管截面重建
勒让特矩
Legendre Moment, Digital Subtraction Angiography, Cross Section Reconstruction
