Land covers mix and high input dimension are two important issues to affect the classification accuracy of remote sensing images. Fuzzy classification has been developed to represent the mixture of land covers. Two fuzzy classifiers of Fuzzy Rule-Based (FRB) and Fuzzy Neural Network (FNN) were studied to illustrate the interpretability of fuzzy classification. A hierarchical structure was proposed to simply multi-class classification to multiple binary classification to reduce computation time caused by high number of inputs. The classifiers were compared on the land cover classification of a Landsat 7 ETM+ image over Rio Rancho, New Mexico, and it was proved that Hierarchical Fuzzy Neural Network (HFNN) classifier is the best combination of better classification accuracy with shorter CPU time requirement.