Fast Matching between Volume and Image

The goal of this paper is to present a fast matching method between three-dimensional volume and two-dimensional image. The new method is based on a hybrid similarity measure taking consideration of the boundary/edge, as well as image intensity, thus can be seen as some combination of the geometry-based and intensity-based method. In addition, it is suitable for parallel computation, and the performance is accelerated by multi-core processors through the use of multiple threads. The results demonstrate that the proposed method has good balance between accuracy and speed, and has potential for the image guided surgery.