Learning Corner Orientation Using Canonical Correlation

This paper shows how canonical correlation can be used to learn a detector for corner orientation invariant to corner angle and intensity. Pairs of images with the same corner orientation but different angle and intensity are used as training samples. Three different image representations; intensity values, products between intensity values, and local orientation are examined. The last representation gives a well behaved result that is easy to decode into the corner orientation. To reduce dimensionality, parameters from a polynomial model fitted on the different representations is also considered. This reduction did not affect the performance of the system.