Contact-free hand geometry identification system

Abstract

This paper presents an approach for personal identification using hand geometrical features, in which the infrared illumination device is employed to improve the usability of this hand recognition system. In the proposed system, prospective users can place their hands freely in front of the camera without any pegs or templates. The system can also work in normal environment, since no dark background is required. The idea behind the proposed system is to locate the tip of the middle finger and then rotate the palm image according to the tip point. Moreover, additional 12 important points are further identified and 30 features are defined from the information of those points. In addition, the Support Vector Machine (SVM) was used for distinguishing various hands. Experimental result shows an average Correct Identification Rate (CIR) of 98.75%, which is an encouraging consequence for a contact-free hand geometry identification system.