<![CDATA[Oral health is a condition in which the hard and soft tissues in the oral cavity are healthy, free from disease, and aesthetic disorders. One of the main problems faced is dental caries, a disease that starts from damage to the tooth surface and can spread to the pulp. Consumption of sweet foods is often the main cause of tooth decay and caries. This study aims to develop a system that is able to recognize carious and non-carious teeth using a Convolutional Neural Network (CNN) with the Vgg-16 architecture. The dataset used consists of 500 images, with a division of 80% for training data, 10% for validation data, and 10% for test data. This study also evaluates the performance of the model using three different optimizers: Adam, Adamax, and RMSprop. The experimental results show that the use of the Adam optimizer produces an accuracy of 77%. Meanwhile, Adamax produces an accuracy of 79%, and RMSprop produces an accuracy of 70%.]]>
Copyrights © 2025
