COVID-19 is an infectious disease caused by a family of coronaviruses, namely severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The fastest method to identify the presence of this virus is a rapid antibody or antigen test, but to confirm the positive status of a COVID-19 patient, further examination is recommended. Lung examination using chest radiography images taken through X-rays of COVID-19 patients can be one of the method to confirm the patient's condition before/after the rapid test. In this paper, a model to detect COVID-19 through chest radiography images is proposed by using a combination of Discrete Wavelet Transform (DWT) and Moment Invariant features, and the Artificial Neural Network (ANN) classifiers. In this case, the haar wavelet transform and seven Hu moments were used to extracting the image's features. The main aim of the work is to find the best features and ANN model for predicting chest radiography images as COVID-19 suspect, pneumonia, or normal. The k-fold crossvalidation test on the best parameters obtained accuracy up to 86.32%, a precision level of 86.35%, and a recall rate of 86.26%.