Hand-Based Gender Recognition Using Biometric Dispersion Matcher

Abstract

This paper presents a novel method for gender recognition through anthropometric hand information. From a visual hand database of a hundred users and distributed in an unbalanced way, contains more men than women. It is designed a simple method to get some length and width measurements from the hand. This information has been passed through a quadratic discriminant classifier called Biometric Dispersion Matcher (BDM) that provides relevant information. In a first step, a discriminative threshold is applied in order to discard those measures which do not have enough information for gender recognition. In a second step, it provides a vector of the main measures. And, finally, it achieves performance rates from 95%, with a train data set of only 18 men and 9 women, to 98%, with a higher training data set.