Chamfer matching is a simple, accurate, reliable, and fast registration method for segmented images. It may be considered as an efficient and flexible implementation of the iterative closest-point matching algorithm. With careful tuning, the method achieves subpixel accuracy. In general, chamfer matching is extremely robust against missing data, low resolution, and poor segmentation of the images. In the presence of artifacts, minimization of the average distance outperformed minimization of the root-mean-square distance. Outliers in the scan from which the point list is obtained must be avoided. 3D image integration plays an important role in assessing and improving the accuracy of radiotherapy.
Was this article helpful?