A two-step verification-based multimodal-biometric authentication system using KCP-DCNN and QR code generation

For providing enhanced authentication performance, the concept of multi-biometrics authentication systems has emerged as a promising solution in today’s digital era. In the existing literature, numerous studies were inefficient in combining biometric and non-biometric images for authentication and differentiating real and forged biometric data. Thus, this paper presents an effective multimodal Biometric Authentication (BA) technique utilizing a Kernel Correlation Padding-based Deep Convolutional Neural Network (KCP-DCNN). Here, signature, fingerprint, and face modalities are combined. Initially, the input images are preprocessed for image magnification utilizing the RBF-PRT and image augmentation utilizing LZS-GAN. Afterward, the FDAF-SACM-based contour extraction, Chaincode-centric minutia extraction, and Dlib’s 68-centric facial point extraction are performed using the magnified signature, magnified fingerprint, and augmented face images, respectively. Next, a Quick Response (QR) code is generated from the extracted points. Then, significant features are extracted for efficient biometric recognition utilizing KCP-DCNN. If the output of biometric recognition is real, then the user is authenticated after the verification of the QR code. The proposed model is accessed using the SOCOFing and Face recognition datasets, which improves the performance and effectiveness of biometric recognition systems. The user identity is recognized by the developed model with 98.732% accuracy and 98.612% precision. Thus, the authentication rate of the Multimodal Biometric (MB) system is increased by the proposed system.