Automatic Personal Identification based on Contour Lines of Human Profiles

Application to the Entrance Control System

Abstract

This paper proposes a new algorithm of the automatic personal identification and the practical application of the algorithm to the entrance control system using extracted contour lines and feature points from human face profiles and summarizes the simulation results of the identification. As a decision function for the identification, we use a weighted distance between the registered 19 dimensional feature vector and the 19 dimensional feature vector of the input profile. The components of the 19 dimensional feature vector are the distances between two feature points and the angles between two lines connecting three consecutive feature points. The 11 feature points are extracted from a contour line of the input profile expressed by Freeman's chain code using digital curvatures of the line. The effects of deformation of profiles caused by face panning and tilting and mouth opening upon identification accuracy have been investigated in details. To overcome the deformation effects we propose to register three profiles per person: a normal head position profile, a tilted profile and a panned profile. The simulation results by 74 subjects show that the identification accuracy for same persons is 80.6_??_97.2% and discrimination accuracy for different persons is 98.1_??_91.1%. This proves the superiority of the proposed algorithm.