System for Fusion of Face and Speech Modalities Using DTCWT+QFT and MFCC+RASTA Techniques

Objectives: The main objective is to propose a multimodal biometric system by forming fusion of Face and Speech modalities using DTCWT+QFT techniques for face MFCC+RASTA Techniques recognitions. experimental results are compared with existing works analysed the performance counterparts. Methods: proposed model, make use DTCWT QFT extract features images perform both. MFCC RASTA implemented speech data then applied. Various databases discussed utilized both recognition proposed. Findings: experimentation systems analysis proved than placed in better position. parameters such as False Acceptation Ratio (FAR), Rejection (FRR), Total Success Rate (TSR), Partial Error (PER), Equal (EER) tabulated six different types sets. average four showed that performs better. measured calculating accuracy, precision, recall F1-score. These five schemes traits human Novelty: Fusion two algorithms analysed. Then novel approach presented combine single improve security biometrics. Keywords: DTCWT; QFT; RASTA; MFCC; Feature Extraction;