Multimodal Biometric System Using Alex Net Model
T R Yashavanth, M Suresh · 2023
The multimodal biometric system combines more than one biometric modality into a single method to overcome the limitations of uni-modal biometric systems. In a multimodal biometrics system, using different algorithms for feature extraction, fusion at the feature level, and classification often leads to complexity and make fused biometrics features larger in dimensions. In this paper convolution neural network using Alexnet based on a deep learning model was employed for training, classification, and testing of the system. The developed multimodal biometrics system was evaluated on a dataset of 1500 images including face, iris, and fingerprint images of ten different people. Experimental results on the datasets have shown significant capability for the identification of biometric systems. The proposed model achieves 96.7 percent classification accuracy, 0.75 precision, 0.8 recall, and an F1 score of 0.867 with 5-fold cross-validation.