Improved human identification by multi-biometric image sensor integration with a deep learning approach

The growing need for data security and security regulations has made biometric identification technology an everyday element of daily life. Multimodal biometrics has gained popularity and attention in this regard since it can resolve a number of the basic limitations of unimodal biometric systems. This study provides a unique multimodal biometric person identification system for iris and face biometrics that depends on a VGG19 with softmax classifier (VGG19-SC). The system’s architecture is built on VGG19-SC, which extracts features from and categorizes images. The system was created by combining the iris and face portions of two VGG19-SC models. VGG-19 was employed to construct the well-known pertained model. A few techniques, such as dropout’s approaches and image augmentation were employed to avoid overfitting. The VGG19-SC models were fused using feature-level and score-level fusion methods to investigate the effects of these fusion methods on recognition performance. As a consequence, the findings showed that in biometric identification systems, three biometric characteristics were more effective than two or one. The findings similarly demonstrated the suggested method easily surpassed other cutting-edge approaches by obtaining an accuracy of 99.39% in a multi-biometric verification system.