Corner detection and curve representation by circularhistograms ofcontour chain code

Abstract

A new algorithm is proposed for representing and characterising the contours of 2D objects, as well as detecting their corners. The novelty lies in the curvature estimation technique which is based on circular histograms of the contour chain code. Two histograms are calculated at the neighbourhood of every point, and instead of considering them of linear type and being compared by correlation, they are considered to be circular and compared by a new method which defines a circular mean of variable origin. The main advantages of this method are its low computational overhead and the precision of the obtained curvature functions.