Coarseness Fuzzy Partitions applied to Texture Image Retrieval
Jesús Chamorro, Pedro Manuel Martinez Jimenez, Jose Manuel Soto-Hidalgo · 2010
In this paper, the texture feature is modelled by means of a fuzzy partition on the domain of coarseness measures. The number of linguistic labels to be used, and the parameters of the membership functions associated to each fuzzy set are calculated relating representative coarseness measures (our reference set) with the human perception of this texture property. A wide variety of measures is studied, analyzing its capability to discriminate difierent coarseness categories. Data about the human perception of flneness is collected by means of a pool and it is used to obtain a fuzzy partition adapted to the human perception of coarseness-flneness. This fuzzy partition is applied to texture image retrieval.