Deep Learning Approach for Ear Recognition and Longitudinal Evaluation in Children

TL;DR

This paper introduces a deep learning-based ear recognition method evaluated on a new longitudinal dataset of children aged 4 to 14, addressing challenges posed by ear changes over time.

Contribution

It presents a novel longitudinal dataset for children's ear recognition and evaluates a deep learning approach tailored for this demographic and age-related changes.

Findings

Deep learning models achieve promising accuracy on children's ear recognition.

Longitudinal evaluation reveals challenges and potential for age-invariant recognition.

Ensemble of VGG16 and MobileNet improves recognition performance.

Abstract

Ear recognition as a biometric modality is becoming increasingly popular, with promising broader application areas. While current applications involve adults, one of the challenges in ear recognition for children is the rapid structural changes in the ear as they age. This work introduces a foundational longitudinal dataset collected from children aged 4 to 14 years over a 2.5-year period and evaluates ear recognition performance in this demographic. We present a deep learning based approach for ear recognition, using an ensemble of VGG16 and MobileNet, focusing on both adult and child datasets, with an emphasis on longitudinal evaluation for children.