Comparing Cornerness Measures for Interest Point Detection

Abstract

Interest point detection is used in many computer vision applications that require fast and efficient feature matching. For tasks such as robot localisation and navigation, the use of interest points for matching is preferred over edges or other, larger, features. Recently, finite-element based methods have been used to develop gradient operators for edge and interest point detection. We extend this work to alternative corner detection measures and provide a comparative evaluation of some different techniques.