Abstract:

The selection of dictionary is crucial to sparse representation classification.In order to preserve the localinformation of original training samples with less dictionary atoms and include more discriminant information in thelearned dictionary,a new dictionary learning method based on the locality preserving criterion is proposed for sparserepresentation.In this method,the locality preserving criterion is imposed on coding coefficients,which makes thecoding coefficients of neighboring data points in the dictionary close to each other and preserves the local informa-tion of original training samples.Experimental results on extended YaleB,AR and COIL20 databases show that theproposed method is effective because it is of higher classification performance than other methods.

Key words: locality preserving, sparse representation, dictionary learning, pattern recognition