Corner Detection With Covariance Propagation

This paper presents a statistical approach for detect-ing corners from chain encoded digital arcs. An arc point is declared as a corner if the estimated parameters of the two fitted lines of the two arc segments immediately to the right and left of the arc point are statistically significantly different. The corner detection algorithm consists of two steps: corner detection and optimization. While corner de-tection involves statistically identifying the most likely cor-nerpoints along an arc sequence, corner optimization deals with improving the locational errors of the detected corners. The major contributions of this research include devel-oping a method for analytically estimating the covariance matrix of the fitted line parameters and developing a hy-pothesis test statistic to statistically test the difference be-tween the parameters of two fitted lines. Performance eval-uation study showed that the algorithm is robust and ac-curate for complex images. It has an average misdetection rate of 2.5 % and false,alarm rate of 2.2 % for the complex RADIUS images. This paper discusses the theory and per-formance characterization of the proposed corner detector. 1