Accurate matching of two-dimensional shapes using the minimal tolerance zone error

Automated visual geometric inspection of machined parts depends upon the ability to determine the underlying parameters of a shape model that will best fit the reference shape to the real shape captured. This paper presents a parametric approach for the matching of two-dimensional profiles, which are composed of straight-line segments and circular arcs, based on the tolerancing requirements defined by the AINSI standards. The shape matching problem is formulated as a minimax optimization model and a procedure for solving this optimization model is developed. Experimental results have shown the proposed algorithm to be consistently accurate and extremely fast.