the recognition of handwritten documents, which aims at transforming the written text into machine-encoded text, is considered as one of the most challenging problems in the area of pattern recognition and an open research area. This brings the necessity to make research works on character recognition of the English alphabet not only recognizing measure and evaluate the performance of algorithms we used. A number of algorithms have been proposed for English character recognition such as a support vector machine, hidden Markov model, and neural network. In this research, the design and implementation of a character recognition system for English characters using artificial neural networks and template matching are presented. The complete system employs image acquisition, preprocessing, character segmentation, and classification and recognition. Finally, compare the performance of ANN and template matching algorithms. A data was an MNIST dataset taken from the NIST database. Overall, a recognition of ANN accuracy of 88 percent was obtained and template matching accuracy was 73 percent.