The research of corner detector of teeth image based on the curvature scale space corner algorithm

In order to detect the corners of the teeth image, which were acquired by oral cavity endoscope, in this paper, we used the CSS algorithm. In this method, firstly, we removed the noise of the image by the morphology open operation and median filtering; secondly, we segmented the image by the threshold based on the gray value of the image; thirdly, we detected the edge of the teeth image by the Canny edge detector; last, we detected the corners by the adaptive threshold curvature scale corner detector. Through lots of experiments and we compare this method to other corner detector methods; this method can detects the corners of the teeth image effectively, which offers some available parameters for the 3D reconstruction of the teeth.