Transformation Network Model for Ear Recognition

Biometrics is the recognition of a human using biometric characteristics for identification, which may be physiological or behavioural. The physiological biometric features are the face, ear, iris, fingerprint and handprint; behavioural biometrics are signatures, voice, gait pattern and keystrokes. Numerous systems have been developed to distinguish biometric traits used in multiple applications, such as forensic investigations and security systems. With the current worldwide pandemic, facial identification has failed due to users wearing masks; however, the human ear has proven more suitable as it is visible. This paper presents the main contribution to presenting the results of a CNN developed using Transfer Learning to pre-train the CNN before applying a Transformer Network. The performance achieved in this research shows the efficiency of the Transformer Network on ear recognition. The experiments showed that Transformer Network achieved the best accuracy of 92.60% and 92.56% with epochs of 50 and 90.