The key to successful morphological image processing is the selection of structuring elements. There are a myriad of algorithms for a multitude of imaging applications, but in each and every instance, algorithm performance depends on the structuring elements. The classical approach to morphological processing is to have a human being, or a group of human beings, use intuition and an understanding of the goals to design algorithms based on erosions, openings, hit-or-miss transforms and other basic morphological operators. This approach can work well if the task can be described in elementary geometric terms and the images under consideration are not too complex. It breaks down in situations where satisfactory filtering might require hundreds, or even thousands, of structuring elements. The present chapter introduces automatic algorithm design, where morphological operators are designed based on sample data, structural decomposition, and criteria set by the imaging scientist.
|