In this paper, a classification method designed by com- bining a local averaging classifier and a tangent distance is proposed for handwritten digit pattern recognition. In practice, first the k-nearest neighbors of an input sample are selected in each class by using a two-sided tangent dis- tance. Next, the mean vectors of the selected transformed- neighbor samples are computed in individual classes. Fi- nally, the input sample is classified to the class that mini- mizes the one sided tangent distance between the input sam- ple and the mean one. The superior performance of the pro- posed method is verified with the experiments on benchmark datasets MNIST and USPS.