Dynamic Hand Gesture-Based Person Identification Using Leap Motion and Machine Learning Approaches

Person identification is one of the most vital tasks for network security. People are more concerned about their security due to traditional passwords becoming weaker or leaking in various attacks. In recent decades, fingerprints and faces have been widely used for person identification, which has the risk of information leakage as a result of reproducing fingers or faces by taking a snapshot. Recently, people have focused on creating an identifiable pattern, which will not be reproducible falsely by capturing psychological and behavioral information of a person using vision and sensor-based techniques. In existing studies, most of the researchers used very complex patterns in this direction, which need special training and attention to remember the patterns and failed to capture the psychological and behavioral information of a person properly. To overcome these problems, this research devised a novel dynamic hand gesture-based person identification system using a Leap Motion sensor. This study developed two hand gesture-based pattern datasets for performing the experiments, which contained more than 500 samples, collected from 25 subjects. Various static and dynamic features were extracted from the hand geometry. Random forest was used to measure feature importance using the Gini Index. Finally, the support vector machine was implemented for person identification and evaluate its performance using identification accuracy. The experimental results showed that the proposed system produced an identification accuracy of 99.8% for arbitrary hand gesture-based patterns and 99.6% for the same dynamic hand gesture-based patterns. This result indicated that the proposed system can be used for person identification in the field of security.