Fuzzy quantifiers, i.e. operators intended to provide a numerical interpretation of natural language (NL) quantifiers like `almost all', are valuable tools for image processing, in particular to express accumulative (second order) properties of fuzzy image regions. However, approaches to fuzzy quantification will unfold their full potential only if the proposed operators capture the meaning of NL quantifiers. We present an exemplary evaluation of one of the most prominent approaches to fuzzy quantification, Yager's OWA approach [Yager 1988], with respect to its suitability to model NL quantification over fuzzy image regions.
I. Glöckner and A. Knoll
Application of Fuzzy Quantifiers in Image Processing: A Case Study
In Proceedings of the Third International Conference on
Knowledge-Based Intelligent Information Engineering Systems
(KES `99), Adelaide, Australia, Aug./Sep. 1999
[to appear]