Abstract
Biometric technology plays a crucial role in cybersecurity by verifying individuals through their distinct physical and behavioral characteristic. As a highly accurate and effective physical security solution, biometrics relies on intrinsic traits that are challenging to duplicate or steal, making it an ideal method for identity verification. Various biometric modalities, including facial recognition, fingerprint scanning, iris scanning, palm print analysis, and ear shape identification, are used to authenticate an individual’s identity. This study presents the design and simulation of a human identification system using ear detection. The proposed system aims to overcome the limitations of existing biometric systems, such as fingerprint and facial recognition, which can be affected by various factors like lighting, facial expressions, and skin conditions. The system uses a novel parameterization process to detect and recognize human ears, leveraging the unique characteristics of ear shapes. A 3D Morphable Ear Model (3DMEM) is created using a non-rigid Iterative Closest Point (ICP) algorithm, and principal component analysis is used to reduce the dimensionality of the data. The system is trained using a labeled dataset, and its performance is evaluated using precision metrics. The results demonstrate the effectiveness of the proposed system in recognizing individuals based on their ear images, The detection rate shows over 95% accuracy. This study contributes to the development of a robust and reliable human identification system, with potential applications in various fields, including security, surveillance, and identity verification.