Towards Explainable Ear Recognition Systems Using Deep Residual Networks

Towards Explainable Ear Recognition Systems Using Deep Residual Networks

This paper presents ear recognition models constructed with Deep Residual Networks (ResNet) of various depths. Due to relatively limited amounts of ear images we propose three different transfer learning strategies to address the ear recognition problem. This is done either through utilizing the Res...

Full description

Bibliographic Details
Main Authors: Hammam Alshazly, Christoph Linse, Erhardt Barth, Sahar Ahmed Idris, Thomas Martinetz
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Ear recognition
biometrics
deep residual networks
transfer learning
deep ensembles
visual explanations
Online Access:https://ieeexplore.ieee.org/document/9526589/

Internet

https://ieeexplore.ieee.org/document/9526589/

Similar Items