Robust multimodal biometric authentication on IoT device through ear shape and arm gesture

Nowadays, authentication is required for both physical access to buildings and internal computers systems. Biometrics are one of the emerging technologies used protect these highly sensitive structures. However, biometric systems based on a single trait enclose several problems such as noise sensitivity vulnerability spoof attacks. In this regard, we present in paper fully unobtrusive robust multimodal system that automatically authenticates user by way he/she answers his/her phone, after extracting ear arm gesture modalities from action. To deal challenges facing real-world applications, propose new method image fragmentation makes recognition more relation occlusion. The feature extraction process has been made locally using Local Phase Quantization (LPQ) order get robustness with respect pose illumination variation. We also set four statistical metrics extract features signals. two combined score-level weighted sum. evaluate our contribution, conducted experiments demonstrate contribution each biometrics advantage their fusion overall performance system. achieves an equal error rate (EER) 5.15%.