Hybrid verification method based on finger-knuckle analysis and keystroke dynamics

The increasing number of personal data leaks becomes one of the most important security issues hence the need to develop modern computer user verification methods. In the article, a potential of biometric methods fusion for continuous user verification was assessed. A hybrid approach for user verification based on fusion of keystroke dynamics and knuckle images analysis was presented. Verification is performed by a classification module where an ensemble classifier was used to verify the identity of a user. A proposed classifier works on a database which comprises of knuckle images and keyboard events for keystroke dynamics. The proposed approach was tested experimentally. The obtained results confirm that the proposed hybrid approach performs better than methods based on single biometric feature hence the introduced method can be used for increasing a protection level of computer resources against forgers and impostors. The paper presents results of preliminary research conducted to assess the potential of biometric methods fusion.