Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Wavelet Texture Descriptor for Steel Surface Defect Classification.

Materials (Basel, Switzerland)·2024

Same author

A fast lightweight network for the discrimination of COVID-19 and pulmonary diseases.

Biomedical signal processing and control·2022

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 6, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

MDFNet: an unsupervised lightweight network for ear print recognition.

Oussama Aiadi¹, Belal Khaldi¹, Cheraa Saadeddine¹

¹LINATI Laboratory, Department of Computer Science and Information Technology, University of Kasdi Merbah, 30000 Ouargla, Algeria.

Journal of Ambient Intelligence and Humanized Computing

|June 27, 2022

Summary

This summary is machine-generated.

We introduce MDFNet, a lightweight network for ear print recognition. This method achieves high accuracy and robustness to occlusion, outperforming existing approaches.

Keywords:

Biometrics CNN Deep learning Recognition Unconstrained ear Unsupervised learning

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Sep 6, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Area of Science:

Biometrics
Computer Vision
Machine Learning

Background:

Ear biometrics offers a unique and stable identification method.
Existing ear recognition systems often struggle with occlusion and varying illumination.

Purpose of the Study:

To propose an unsupervised, lightweight, single-layer network for robust ear print recognition.
To develop a method that balances processing time and recognition performance.

Main Methods:

Ear alignment using Convolution Neural Network (CNN) and Principal Component Analysis (PCA).
MDFNet utilizes gradient Magnitude and Direction with data-driven Filters, including a binary hashing process to prevent overfitting.
Histogram construction for gradient magnitude and direction, normalized using the power-L2 rule.

Main Results:

MDFNet achieved high recognition rates on public datasets: 82.5% (AWE), 97.67% (AMI), and 98.96% (IIT Delhi II).
The method demonstrated superior robustness to occlusion compared to state-of-the-art techniques.
Ear alignment was identified as a critical factor for effective recognition.

Conclusions:

MDFNet presents a simple yet effective architecture for ear print recognition.
The proposed method offers a strong trade-off between computational efficiency and high accuracy.
The findings highlight the importance of addressing occlusion and illumination in biometric systems.