一种快速医学图像亚像素边缘检测方法

A fast subpixel edge measuring method for medical image

针对目前医学图像配准中使用的多是配准精度较低的像素级的边缘检测的问题,提出一种新算法将像素级算子sobel,log,prewitt,roberts,zerocross和canny分别与Zernike矩算子及搜索算法相结合,并对边缘检测结果进行比较,从中选取较优的算子来实现医学图像亚像素边缘检测.实验结果表明该算法克服了像素级算子和Zernike矩算子的缺点,提取的边缘定位精度高,计算时间短,抗干扰性强.

Now most edge detections in medical image registration are in pixel level, with lower registration precision. The presented new algorithm combines pixel-level operators, Zernike orthogonal moment （ZOM） with search algorithm respectively. The results of edge detection are compared. The better are chosen to extract the edge. The experimental results show that the algorithm overcomes the shortcomings of pixel level operator and ZOM, the edge extracted by the algorithm has high locating precision, short operation time and strong robustness to noise.