Based on a distance of kernel method, a novel noise-resistant fuzzy clustering algorithm called kernel noise clustering (KNC) algorithm, is proposed. KNC is an extension of the noise clustering (NC) algorithm proposed by Dave. By replacing the Euclidean distance used in the objective function of NC algorithm, a new distance is introduced in NC algorithm. The distance of the kernel method is more robust than Euclidean and alternative distance. Moreover, The properties of the new algorithm illustrated that the KNC are most suitable and effective method for clusters with non-spherical shapes such as annular ring shape. In addition, KNC is a better method to solve the problems annular ring shape with noise than the FKCM is.