Pattern classification for finding facial growth abnormalities

Cephalometric analysis of lateral radiographs of the head is an important diagnosis tool in orthodontics. Based on actually locating precise landmarks, it is a tedious, long-lasting and error prone mission. The objective of this work is to calculate the SNA angle, SNB angle and ANB angle between the landmarks to identify the input and output parameters pertaining to skeletal abnormalities. By doing so the patients data for training and testing the back propagation neural network (BPNN), generalized regression neural network (GRNN), support vector machine (SVM) and extreme learning machine (ELM) classifiers by nine fold cross substantiation. The presentation of skeletal is originated out using the BPNN, GRNN, SVM and ELM models. This will be useful to identify whether the patient is normal or abnormal (need for treatment). This will categorize situation of the diverse patients with severity of abnormalities in skeletal.