A morphological signature transform for shape description

A novel shape description method based on the multiresolution morphological image processing by non-convex multiple structuring elements is presented. A binary image which contains the object shape to be described is represented by means of a multiresolution pyramid. A set of primary structuring elements along with their rotated versions is used. The method is based on the successive morphological erosions of the input image at different resolutions by primary and rotated structuring elements. The areas of successively eroded images are computed for each structuring element at each pyramid level. The obtained set of numbers is arranged into vectors, ordered, and used as a shape descriptor. Results are included to show that the method is robust against noise and invariant to both rotation and scale change.