基于C型臂手术导航技术的XRⅡ图像中标志物识别及数据提取*☆

XRII图像中标志物的识别及数据提取是基于C型臂手术导航关键技术之一。现有方法可靠性差，检测精度低。本文提出一种混合标志物检测算法。首先通过一种改进CHT法获取参数空间，并获取其横切面二值化图像；而后进行连通分量分析，识别出其中的圆形体并提取其面积及中心坐标数据。改进CHT对掩模及积分算子进行了重新定义；连通分量分析则采用一种新的圆形测度。实验表明所提算法具有更高检测率、检测精度及可靠性。

Detecting objects in XRII images for C-arm based surgical navigation

It is a key technique of C-arm based surgical navigation to recognize circular objects and extract their geometric data from XRII images. Existing methods possess low detecting & extracting accuracy & reliability. In this paper, we proposed a hybrid object detecting algorithm. Firstly, an improved Circle Hough Transform was used to obtain the accumulative space, then the section of the space was used to acquire a binarized image. Secondly, connected component analysis method was used to recognize circular objects and extract their areas and center coordinates. In the improved CHT, mask and integral operator were redefined. In the CC analysis, a new circle measurement was used. Results of experiments showed that the proposed algorithm possesses higher detecting ratio, higher detecting accuracy, and better reliability.