The rapid advancement of contemporary technological assets in current decades has required the development of precise customer recognition systems in order to regulate accessibility to these technologies. Biometrics refers to the scientific field that involves the identification of individuals through the use of partially or fully automated systems, which rely on behavioral characteristics (e.g., voice or signature) and/or physical characteristics (e.g., iris and fingerprint). Biometric recognition systems can be categorized into two main types: unimodal and multimodal. The unimodal system employs a one biometric characteristic for the purpose of user recognition. Although unimodal systems have demonstrated their trustworthiness and superiority over traditional approaches, it is important to acknowledge their inherent limits. Multimodal biometric systems necessitate the utilization of many biometric traits in order to accurately identify and authenticate users. The benefits inherent in multimodal biometric systems in comparison to unimodal systems have rendered them a highly appealing option for reliable recognition. Multimodal technological innovation in biometrics has garnered attention and achieved widespread popularity owing to its capacity to address certain notable constraints associated with unimodal biometric systems. This research introduces an advanced multi-modal biometric identification system that utilizes a customized deep learning model for the purpose of verifying individuals based on various biometric characteristics, including Face, Iris, Finger, Palm, and Ear.