Hand Geometry Feature Extraction Through Curvature Profile Analysis

Boreki, Guilherme1; Zimmer, Alessandro2

1,2 UNICENP - Centro Universitário Positivo, Departamento de Computação

Abstract. In this work a complete access control system based on a biometric code formed by invariant geometric features extracted from the hand’s image, a hardware key and a vital sign detector. The feature extraction process is based on the analysis of the curvature profile of the image, making the system invariant to the rotation and translation of the hand. This makes unnecessary the use of any kind of restriction devices such as pins or pegs to position the hand. FAR rates as low as 0.8% was obtained by the use of simple weighted geometric features on a database of more than 360 hand images.

[ project home page | contact authors ]

pictures and other stuff here.

Figure 1. Hand contour with high curvature markings.

Figure 2. Contour with the extracted features based on the markings from figure 1.

Figure 3. FAR x FRR graph showing an Equal Error Rate (EER) of 3.8%.

Figure 4. Features extraction in a regular hand image

Figure 5. Features extraction in a nearly closed hand

Figure 6. Features extraction in rotated hand

Figure 7. Features extraction in wide open hand