An evaluation of a three-modal hand-based database to forensic-based gender recognition

In recent years, behavioural soft-biometrics have been widely used to improve biometric systems performance. Information like gender, age and ethnicity can be obtained from more than one behavioural modality. In this paper, we propose a multimodal hand-based behavioural database for gender recognition. Thus, our goal in this paper is to evaluate the performance of the multimodal database. For this, the experiment was realised with 76 users and was collected keyboard dynamics, touchscreen dynamics and handwritten signature data. Our approach consists of compare two-modal and one-modal modalities of the biometric data with the multimodal database. Traditional and new classifiers were used and the statistical Kruskal-Wallis to analyse the accuracy of the databases. The results showed that the multimodal database outperforms the other databases.