Training Convolutional Neural Networks with Limited Training Data for Ear Recognition in the Wild

TL;DR

This paper develops a CNN-based ear recognition model trained with limited data, employing data augmentation and transfer learning, achieving significant accuracy improvements on in-the-wild datasets.

Contribution

It introduces the first publicly available CNN approach for ear recognition that works effectively with just over 1300 images and surpasses previous state-of-the-art performance.

Findings

Over 25% improvement in rank-one recognition rate

Effective CNN model trained with limited data

Model is publicly available for research use

Abstract

Identity recognition from ear images is an active field of research within the biometric community. The ability to capture ear images from a distance and in a covert manner makes ear recognition technology an appealing choice for surveillance and security applications as well as related application domains. In contrast to other biometric modalities, where large datasets captured in uncontrolled settings are readily available, datasets of ear images are still limited in size and mostly of laboratory-like quality. As a consequence, ear recognition technology has not benefited yet from advances in deep learning and convolutional neural networks (CNNs) and is still lacking behind other modalities that experienced significant performance gains owing to deep recognition technology. In this paper we address this problem and aim at building a CNNbased ear recognition model. We explore different strategies towards model training with limited amounts of training data and show that by selecting an appropriate model architecture, using aggressive data augmentation and selective learning on existing (pre-trained) models, we are able to learn an effective CNN-based model using a little more than 1300 training images. The result of our work is the first CNN-based approach to ear recognition that is also made publicly available to the research community. With our model we are able to improve on the rank one recognition rate of the previous state-of-the-art by more than 25% on a challenging dataset of ear images captured from the web (a.k.a. in the wild).