A Deep Learning Approach based on Faster R-CNN for Automatic Detection and Classification of Teeth in Orthopantomogram Radiography Images

This paper presents a new method for teeth and anomalies detection and classification using Faster Region Convolutional Neural Network with Deep Learning. Four classes of teeth and two classes of teeth anomalies are used for the classification by using Orthopantomogram radiography images as input. Using the Regional Proposal Network (RPN) and Object Detection Network (ODN), the detection of teeth objects has been made possible which replaces the manual segmentation of each individual tooth from the set of teeth signals thereby making the whole system more efficient. Overfitting is avoided by using the Dropout technique and thus improves the accuracy of the system. The model is trained and tested with the input samples and also compared with the ground truth and it achieves an accuracy of 92% for detection and 99.72% for classification.