In pattern recognition based on sparse representation classification,concise representation of data can be obtained fo r sparse representation via dictionary learning.Recently,Fisher discrimination d ictionary learning ( FDDL) can obtain very discriminant sparse dictionary,which will bring high reco gnition performance for sparse representation classification.Transforming data into kernel spaces usually can learn non-line ar structure information, which is very useful for discrimination and classification.To make full use of properties of kernel space transformation and to learn more discriminant dictionaries for higher recognition performance,t w o new dictionary learning methods,based on FDDL,are proposed for kernel sparse representation classificati on.First,the original training data are projected into high dimensional kernel space and then Fisher discrimination ker nel dictionary learning (FDKDL) is proposed for kernel sparse representation classification.Second,kernelized Fi sher discrimination criterion is imposed on the sparse coefficients,and then ker nelized Fisher discrimination kernel dictionary learning (KFDKDL) is proposed fo r kernel sparse representation classification,which makes the obtained dictionar y have higher discrimination ability.Experiments of sparse representation-based classification on several p ublic image databases demonstrate the effectiveness of the proposed FDKDL and KFDKDL dictionary learning methods.