A fuzzy approach for texture contrast modelling

In this paper, we propose to model the contrast of visual texture by means of a perceptual-based fuzzy approach. For this modelling, fuzzy sets defined on the domain of some of the most representative measures of the contrast property are employed. In order to obtain these fuzzy sets, a functional relationship between the computational values given by the measures and the human perception of contrast is learned. The goodness of each model is analyzed and tested with the human assessments, allowing us to identify the most suitable one to represent the contrast of visual texture. Finally, several experiments are performed in order to show the application of the proposed fuzzy model for pattern recognition.