Unconstrained ear recognition using transformers

Abstract EN

The advantages of the ears as a means of identification over other biometric modalities provided an avenue for researchers to conduct biometric recognition studies on state-of-the-art computing methods.

This paper presents a deep learning pipeline for unconstrained ear recognition using a transformer neural network: Vision Transformer (ViT) and Data-efficient image Transformers (DeiTs).

The ViT-Ear and DeiT-Ear models of this study achieved a recognition accuracy comparable or more significant than the results of state-of-the-art CNN- based methods and other deep learning algorithms.

This study also determined that the performance of Vision Transformer and Data-efficient image Transformer models works better than that of ResNets without using exhaustive data augmentation processes.

Moreover, this study observed that the performance of ViT-Ear is nearly like that of other ViT-based biometric studies.