An approach for X-ray image mosaicing based on Speeded-Up Robust Features

Image mosaicing is a common method in Medical image processing. In this paper, a new method is proposed for image mosaicing based on Speeded-Up Robust Features (SURF), which can be used for X-ray images of spine. First, feature descriptor of the image is obtained by using SURF; secondly, matching pairs are found, check the neighbors, and remove the mismatch couples by RANSAC (Random Sample Consensus); then, adjust the images and estimate the accurate homo-graphy matrix; lastly, stitch image by weighted average method. The experimental results show that the method can be effectively applied for prototype panoramic X-ray imaging.