Prediction of the Facial Growth Direction is Challenging

Facial dysmorphology or malocclusion is frequently associated with abnormal growth of the face. The ability to predict facial (FG) direction would allow clinicians prepare individualized therapy increase chance for successful treatment. Prediction FG a novel problem in machine learning (ML) domain. In this paper, we perform feature selection and point attribute that plays central role abovementioned problem. Then successfully apply data augmentation (DA) methods improve previously reported classification accuracy by 2.81%. Finally, present results two experienced were asked solve similar task ours show how tough solving human experts.