Shape Retrieval: A Look at the First Moment Invariant Method

The moment invariant method for shape retrieval was first proposed by Khotanzad and Hong in 1990. They introduced a set of seven moment invariants that could be used to describe the shape of an object, regardless of its size, orientation, or position. These moment invariants were based on the central moments of the object's boundary, and were calculated using a polar coordinate system. The method was shown to be effective for shape matching and recognition, and has since been widely used in computer vision and pattern recognition applications.