The moods, emotions, and even medical issues of a person can frequently be seen directly reflected in their facial expressions. The fields of social science and human-computer interaction have recently begun to pay more attention to facial emotion detection as a result of this. The primary focus of this study is on the automatic recognition of human facial expressions using an artificial neural network (ANN) model and a technique based on straightforward convolution. The dataset utilized is a self-mined dataset that was obtained by utilizing the web scraping approach on Google Image with the help of the Selenium package for Python. A dataset containing six categories of fundamental human expressions that are likely to be met on a daily basis, namely anger, confusion, contempt, crying, sadness, disgust, and happiness, with a total of 6,016 photos being used. The goal of this research is to determine how accurate the model of artificial neural networks can be in predicting.