Multispectral images segmentation using fuzzy probabilistic local cluster for unsupervised clustering

In Pattern Recognition there are many algorithms it try to solve the problem of grouping objects of the same type, this is called clustering, however the task of dividing these lies not only in the objective function, but also the methodology used to calculate the similarity between objects. Because multispectral images contain information that has low statistical separation and a large amount of data it is necessary to enter local information. In this paper, the use of the Gaussian dispersion equation is proposed in order to calculate the contribution of each sample to the sample analyzed. The results show that the integration of local weights within the clustering model decreases the entropy of each group generated.