A Simple Yet Effective Approach for Recognition of Convex Geometric Shapes

Abstract

Automated shape recognition is a common problem which has been faced in computer vision applications. The feature(s) used to identify shapes is important for an accurate and fast method. Perimeter curve analysis is a widely used feature basis in this field because of its quick and easy calculation properties. This study proposes to use perimeter curve inflection points analysis to identify 2D convex geometric shapes. The proposed method is independent from translation, rotation, and scale of the geometric objects.