Kinect User Authentication using Multimodal Biometric

Objectives: Facial Recognition system has been the most popular non-intrusive authentication system. The proposed system offers to improve the accuracy of facial recognition using multimodal authentication with a 3d depth sensor. Methods/Statistical Analysis: To increase the reliability and robust of the system, we superimpose skeletal biometric features with facial features where data combined using 3D Imaging Technology. Statistical approaches are used for feature transformation using PCA and LDA Algorithm. Findings: To evaluate the system, we collected nearly 1000 individuals with two samples for each, captured in indoor environments under various light effects. The accuracy of the system is built with 95% confidence interval and based on a classifier, three performance curves Receiver Operating Characteristics (ROC), Cumulative Match Score Curves (CMC) and Expected Performance Curves (EPC) are used for performance evaluation. The FRR of the proposed multimodal fusion approach is 0.12 at 0.001 minimal FAR with 95% accuracy. Applications/Improvements: Multimodal biometric is required for strong authentication for the surveillance of smart home, cities and health care sectors where security plays a vital role. This fusion technique improves the reliability, latency, and accuracy of the system in recognizing and authenticating the user.