Fuzzy mathematical morphology and its applications to colour image processing

In image analysis and pattern recognition fuzzy sets play the role of a good model for segmentation and classifications tasks when the regions and the classes cannot be strictly defined. One of the most widely used fuzzy approaches in image processing is fuzzy mathematical morphology because of the underlaying structure of complete lattices. Thus, mathematical morphology is used mainly in processing of binary or single - valued intensity (grey - scale) images for which a partial ordering, hence a lattice structure, is apparent. However, the problem of morphological image processing of colour images is that it is not naturally clear how to define ordering in a colour space. This paper shows a possible way for solving this problem. It is based on the usage of YCrCb colour space as physically intuitive and easy to compute