A corner orientation detector

This paper introduces an operator for the detection of the true location and orientation of corners. Its strength in dealing with junctions as well as corners is demonstrated. With this method, corner points are detected as intensity patterns that are anisotropic along several directions. Pixels belonging to the arms of the detected corners are analysed, and a histogram search provides a measure of their dominant orientations. Based on a single derivative scheme proposed by Yang et al. [Structure adaptive anisotropic image filtering, Image and Vision Computing 14 (1996) 135-145] the approach has proved to be insensitive to noise and has been applied to both synthetic and real-life images. (C) 1999 Elsevier Science B.V. All rights reserved.