Current technological developments spur the application of pattern recognition in various fields, such as the introduction of signature patterns, fingerprints, faces, and handwriting. Human handwriting has differences between one another and often handwriting is difficult to read or difficult to recognize and this can hamper daily activities, such as transaction activities that require handwriting. Even one of the biometric features of everyone is handwriting. One method that can be used to recognize handwriting patterns in the field of computer science is artificial neural networks (ANN) with the learning algorithm is backpropagation. Artificial neural networks are able to recognize something based on the past. This means that past data will be studied so as to be able to make decisions on new data. To recognize handwriting patterns using artificial neural networks, the characteristics of handwritten objects are extracted using an invariant moment. The results of training using artificial neural networks indicate that the correlation coefficient value is obtained on the number of hidden layer neurons by 30. The highest correlation coefficient value is 0.61382. The test results on the test data obtained an accuracy rate of 11.67% of the total test data.