SUMMARY
The Covid-19 has been an epidemic that has taken the world by storm since the beginning of 2020. This Covid-19 outbreak can spread easily through the air. Because Covid-19 can transmit easily, the government implements new behavior based on an adaption to develop a clean and healthy lifestyle which is often called the new normal. One way to live the new normal is to wear a mask when leaving the house. To help increase public awareness in using masks, numerous technology- based studies have been carried out. This article explain an application using the python programming language that applies digital image processing in terms of detecting the use of masks using Deep Learning with the Convolutional Neural Network (CNN) method to classify data that has been labeled using the supervised learning method. In designing this CNN architectural model, a total of 2110 images of people wearing and without wearing masks will be used, this dataset will be divided into 2 parts, with a rate of 8020, where 80 of the dataset will be used as training data, 20 is used as validation data. In testing the model by taking a total of 100 images with a 5050 ratio between face images using masks and not using masks tested using a confusion matrix, it produces 97% of an accuracy rate, 100% of precision rate, and 94% of recall in recognizing facial images that use masks and don't use masks