Performance assessment of feature detection algorithms: a methodology and case study on corner detectors

We describe a generic methodology for evaluating the labeling performance of feature detectors. We describe a method for generating a test set and apply the methodology to the performance assessment of the three well-known corner detectors of L. Kitchen and A. Rosenfeld (1982), of K. Paler et al. (1984), and of C. Harris and M. Stephens (1988). The labeling deficiencies of each of these detectors is related to their discrimination ability between corners and various of the features which comprise the class of noncorners.