| 基于多尺度卡尔曼滤波的医学图像配准算法 |
| |
| 引用本文： | 卢振泰,陈武凡.基于多尺度卡尔曼滤波的医学图像配准算法[J].计算机工程与设计,2008,29(19). |
| |
| 作者姓名： | 卢振泰 陈武凡 |
| |
| 作者单位： | 南方医科大学,医学图像处理重点实验室,广东,广州,510515 |
| |
| 基金项目： | 国家重点基础研究发展计划(973计划) |
| |
| 摘 要： | 提出了一种新的基于主成分分析和多尺度卡尔曼滤波的医学图像配准算法.利用主成分分析的方法求出两幅图像的主轴和质心,从而计算出图像间的旋转角度;利用高斯金字塔分解构造了一种自适应的卡尔曼滤波器用来提高算法的鲁棒性.对模拟图像和真实图像进行了实验,实验结果表明此方法能准确,快速地处理图像刚性配准问题.
|
| 关 键 词： | 主成分分析 多尺度卡尔曼滤波 金字塔分解 图像配准 特征值分解 |
Medical image registration algorithm based on multiscale Kalman filters |
| |
| LU Zhen-tai,CHEN Wu-fan.Medical image registration algorithm based on multiscale Kalman filters[J].Computer Engineering and Design,2008,29(19). |
| |
| Authors: | LU Zhen-tai CHEN Wu-fan |
| |
| Affiliation: | LU Zhen-tai,CHEN Wu-fan (Key Lab for Medical Imaging,Southern Medical University,Guangzhou 510515,China) |
| |
| Abstract: | This paper presents a new image registration method,which is based on a combination of two already well-known techniques: the principal component analysis(PCA) and multiscale pyramid decomposition.The PCA analysis is applied to find rotation.The proposed technique is shown to enjoy excellent robustness against noise.We present both simulated and real image examples to demon-strate the proposed technique. |
| |
| Keywords: | principal component analysis multiscale Kalman filters pyramid decomposition image registration eigenvalue de-composition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
