치아 윤곽선 정보를 이용한 신경회로망 기반 신원 확인 방안

Abstract

Received 24 March, 2013; received in revised form 6 May, 2013; accepted 8 May, 2013ABSTRACTThis paper proposes a method for human identification using teeth contours extracted from den-tal images that are captured from the frontal views of subjects each of who opens his or hermouth slightly. Each dental image has a black-colored region containing the subject's teeth con-tours which are usually different from subject to subject. This means that this black-coloredregion has bio-mimetic information useful for human identification. The basic idea of themethod is to extract the upper and lower teeth contours from the dental image of each subjectand to encode their geometric patterns using a back-propagation neural network model. Afteracquiring 400 teeth images form 10 university students, we used 300 images for the trainingdata of the neural network model and 100 images for its verification. Experimental results haveshown that the proposed neural network-based method can be used as an alternative solution foridentification among a small group of humans with a low cost and simple setup.Key Words:Artificial neural networks, Back propagation, Dental images, Human identification,Teeth contour extraction