A method for extracting landmark geometric data from X-ray images / 生物医学工程学杂志

ABSTRACT

Extracting landmark geometric data in C-arm X-ray images is a key technique of camera calibration process in a fluoroscopic-image-based surgical navigation system. The geometric data is the basis of X-ray image distortion correction and C-arm camera calibration. In this paper we present an integrated clustering algorithm for landmark geometric data extraction. This proposed alorithm, with the advantages of an adaptive thresholding method as well as of a fast quasi connected-component labeling method, needs only one pass to extract the needed geometric data in a gray scale image. It is of high executive efficiency and good robustness as well.