In order to detect the corners of the teeth image, which were acquired by oral cavity endoscope, in this paper, we used the improved SUSAN corner detector 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; last we detected the corners of the image through the improved SUSAN corner detector algorithm. Through lots of experiments and comparing with other corner detector methods, this method can detect the corners of the teeth image effectively, which can offer some available parameters for the 3D reconstruction of the teeth.
展开▼