Smart Device-Based Multimodal Biometric Authentication with the Function for Environment Recognition

For smart devices, such as smart-phones and tablet PCs, multimodal biometric authentication can be implemented by integrating multiple sensors, such as cameras and touch panels, mounted on these devices. However, the performance in various usage environments has not always been evaluated sufficiently. In this paper, we propose a multimodal biometric authentication system with a function for recognizing usage environments. The function alleviates the degradation in verification accuracy caused by the difference in usage environments. We also present an evaluation of the performance of the system under different usage environments by focusing on faces and handwriting as acquirable biometric information from the smart devices. The evaluation demonstrates the effectiveness of our system.