<![CDATA[Humans have different faces for each person. Differences in the face such as the shape of the eyes, nose, mouth, eyebrows or face shape. Utilization of technology that can be used as information in the manufacture of facial recognition technology. One of the objects needed in face recognition is face shape. However, there has not been much research on the shape of the human face so that it needs to be done so that it can be used in other fields. The research conducted is by doing classification. There are many classification methods, one of which is Convolutional Neural Network (CNN). CNN is a type of deep learning designed to process two-dimensional data with high network depth. Inspired by the human artificial neural network. In general, it consists of a Convolutional Layer, Pooling Layer and Full Connected Layer. In this study, it is used to classify the shape of the human face into two classes, such as square and round. The total amount of data is 400 data, 80% training data and 20% validation data. The results of this study are getting training accuracy of 0.8188 and validation accuracy of 0.8125. Meanwhile, for 20 test data, the accuracy is 0.75.]]>
Copyrights © 2022
