Rotation-Invariant DAISY descriptor for keypoint matching and its application in 3D reconstruction

In this paper, we introduce an improved version of DAISY descriptor algorithm, which is used for high-quality image keypoint matching. Since DAISY descriptor algorithm has many prominent advantages but lacks the ability of handling large in-plane rotation, we thus construct our Rotation-Invariant DAISY descriptor to effectively settle this shortcoming. The matching results of our scheme can be also used into 3D reconstruction task. After camera parameters are estimated by self-calibration, we compute corresponding 3D data using structure from motion (SFM) technique. Our experimental results demonstrate that Rotation-Invariant DAISY descriptor algorithm has better performance in various image distortions, and it can be effectively applied to the framework of 3D reconstruction.