An Interactive X-Ray Image Segmentation Technique for Bone Extraction
Cristina Stolojescu-Crișan, Ştefan Holban · IWBBIO · 2014
Image segmentation plays a fundamental role in many medi- cal imaging applications by facilitating the contouring of the regions of interest. In this paper, we propose an accurate interactive method which combines two image segmentation techniques. In the rst step, a mean shift segmentation algorithm is used for initial segmentation, followed by an adaptive region merging process based on the maximal similarity between regions, in the second step. The proposed method is tested on a set of real X-ray images and the goal is to separate the bones from the rest of the image. The experimental results on real X-rays show that the proposed segmentation algorithm is highly eective, since it has the ability to extract the contour of the desired objects from the image.