A bi-level hierarchical fuzzy object based approach to natural scene classification

A fuzzy logic based approach for modeling various categories of natural scenes in images is presented. Different local objects occurring in a natural scene are represented as fuzzy semantic objects having various color and texture attributes. The entire scene is viewed as a two-level abstraction hierarchy. At the top level, the scene is considered to be comprised of three separate regions defined across its vertical dimension. At the lower level, each region is viewed as a collection of several local fuzzy objects. The frequency of occurrence of fuzzy objects in various vertical regions is used to determine the scene class. The system has been tested on a standard dataset and shows good results.