Abstract
Mathematical morphology is a relatively new approach that is being applied to image processing and analysis. Mathematical morphology is based on shape. Hence morphological tools are well suited to problems of shape analysis. Shape is conceptually quite abstract, and it is rather difficult to quantify. In this paper a simple quantitative shape descriptor based on a modified image-skeleton spectrum is defined, and experiments to validate its use are described. We attempted to incorporate human ideas of shape into the new shape descriptor. Throughout this paper it is assumed that the reader has a good knowledge of the basic morphological operations and of the skeletonization procedure.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
