A scaling and rotating invariant object matching algorithm

The object detection is a key part of the image processing and machine vision. Several methods were made for the solution of that problem. In this paper, we will introduce an object matching method which is based on the polygonization of objects. First, the contours of the objects are extracted and later the contours should be converted into polygons by a merging method. The similarity between two objects can be measured by the “distance” of the two appropriate polygons.