Gender Identification on the Teeth Based on Principal Component Analysis Representation

Abstract

We present a new approach method for gender identification on the teeth based on PCA (principal component analysis) representation using geometric features of teeth such as the size and shape of the jaws, size of the teeth and teeth structure. In this paper we try to set forth the foundations of a biometric system for automatic evaluation of gender identification using dental geometric features. To create a gender identification system, a template based on PCA is created from dental data collected the plaster figures of teeth which were done at dental hospital, department of oral medicine. Templates of dental images based on PCA representation include the 18 principal components as the features for gender identification. The PCA basis vectors reflects well the features for gender identification in the whole of teeth. The classification for gender identification is generated based on the nearest neighbor (NN) algorithm. The gender identification performance in dental images of 50 person was 76%. The identified values in females and males were 79.3% and 71.4%, respectively.