Robust Ear Biometric Recognition using Neural Network

Mohammad Mozammel Hoque Chowdhury; MD Rafiqul Islam; Junbin Gao

doi:10.1109/ICIEA.2017.8283140

Robust Ear Biometric Recognition using Neural Network

Mohammad Mozammel Hoque Chowdhury, MD Rafiqul Islam, Junbin Gao

The University of Sydney

Research output: Book chapter/Published conference paper › Conference paper › peer-review

16 Citations (Scopus)

Abstract

Ear based biometric recognition has been gaining popularity in recent years because the ear is unique to individuals and generally unaffected by changing pattern over aging. This paper aims to propose a robust and efficient ear biometric recognition scheme using local features of the human ear employing a neural network algorithm. The scheme initially estimates the ear region from the facial image and then extracts the edge features from the detected ear. We use edge local features since they are invariant to illumination changes and occlusion. A neural network is used to recognize the user by matching the extracted ear features of the user with a feature database. The performance of the approach is tested with different datasets and compared with some existing well known methods. Experimental evaluation clearly proves the robustness and effectiveness of the proposed scheme over similar techniques.

Original language	English
Title of host publication	Proceedings of the 2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA)
Place of Publication	United States
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	1855-1859
Number of pages	5
ISBN (Electronic)	9781538621035
DOIs	https://doi.org/10.1109/ICIEA.2017.8283140
Publication status	Published - 08 Feb 2018
Event	2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA) - Royal Angkor Resort & Spa, Siem Riep, Cambodia Duration: 18 Jun 2017 → 20 Jun 2017 http://www.ieeeiciea.org/2017/?utm_source=researchbib (Conference website) https://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8272105 (Conference proceedings)

Conference

Conference	2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA)
Country/Territory	Cambodia
City	Siem Riep
Period	18/06/17 → 20/06/17
Other	The 12th IEEE Conference on Industrial Electronics and Applications (ICIEA 2017) will be held during 18 - 20 June 2017, in Siem Reap, Cambodia. The Conference is organized by IEEE Industrial Electronics Chapter of Singapore and IEEE Singapore Section. IEEE Industrial Electronics Society is the financial and technical sponsor The proceedings of past ICIEA have all been included in the IEEE Xplore database and indexed by EI Compendex and ISI Proceedings. ICIEA 2017 marks the 12th Anniversary of the ICIEA conferences. As a premier conference, ICIEA provides an excellent forum for scientists, researchers, engineers and industrial practitioners throughout the world to present and discuss the latest technology advancement as well as future directions and trends in Industrial Electronics.
Internet address	http://www.ieeeiciea.org/2017/?utm_source=researchbib (Conference website) https://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8272105 (Conference proceedings)

Access to Document

10.1109/ICIEA.2017.8283140

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8283140

Cite this

@inproceedings{0554da94da8947e0b6214bc2f1df286a,

title = "Robust Ear Biometric Recognition using Neural Network",

abstract = "Ear based biometric recognition has been gaining popularity in recent years because the ear is unique to individuals and generally unaffected by changing pattern over aging. This paper aims to propose a robust and efficient ear biometric recognition scheme using local features of the human ear employing a neural network algorithm. The scheme initially estimates the ear region from the facial image and then extracts the edge features from the detected ear. We use edge local features since they are invariant to illumination changes and occlusion. A neural network is used to recognize the user by matching the extracted ear features of the user with a feature database. The performance of the approach is tested with different datasets and compared with some existing well known methods. Experimental evaluation clearly proves the robustness and effectiveness of the proposed scheme over similar techniques.",

keywords = "Biometrics, Ear recognition, Neural network, Biometric authentication, Safety and security",

author = "Chowdhury, {Mohammad Mozammel Hoque} and Islam, {MD Rafiqul} and Junbin Gao",

year = "2018",

month = feb,

day = "8",

doi = "10.1109/ICIEA.2017.8283140",

language = "English",

pages = "1855--1859",

booktitle = "Proceedings of the 2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

note = "2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA) ; Conference date: 18-06-2017 Through 20-06-2017",

url = "http://www.ieeeiciea.org/2017/?utm_source=researchbib, https://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8272105",

}

Chowdhury, MMH, Islam, MDR & Gao, J 2018, Robust Ear Biometric Recognition using Neural Network. in Proceedings of the 2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA). IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 1855-1859, 2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA), Siem Riep, Cambodia, 18/06/17. https://doi.org/10.1109/ICIEA.2017.8283140

Robust Ear Biometric Recognition using Neural Network. / Chowdhury, Mohammad Mozammel Hoque; Islam, MD Rafiqul; Gao, Junbin.
Proceedings of the 2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA). United States: IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 1855-1859.

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - Robust Ear Biometric Recognition using Neural Network

AU - Chowdhury, Mohammad Mozammel Hoque

AU - Islam, MD Rafiqul

AU - Gao, Junbin

PY - 2018/2/8

Y1 - 2018/2/8

N2 - Ear based biometric recognition has been gaining popularity in recent years because the ear is unique to individuals and generally unaffected by changing pattern over aging. This paper aims to propose a robust and efficient ear biometric recognition scheme using local features of the human ear employing a neural network algorithm. The scheme initially estimates the ear region from the facial image and then extracts the edge features from the detected ear. We use edge local features since they are invariant to illumination changes and occlusion. A neural network is used to recognize the user by matching the extracted ear features of the user with a feature database. The performance of the approach is tested with different datasets and compared with some existing well known methods. Experimental evaluation clearly proves the robustness and effectiveness of the proposed scheme over similar techniques.

AB - Ear based biometric recognition has been gaining popularity in recent years because the ear is unique to individuals and generally unaffected by changing pattern over aging. This paper aims to propose a robust and efficient ear biometric recognition scheme using local features of the human ear employing a neural network algorithm. The scheme initially estimates the ear region from the facial image and then extracts the edge features from the detected ear. We use edge local features since they are invariant to illumination changes and occlusion. A neural network is used to recognize the user by matching the extracted ear features of the user with a feature database. The performance of the approach is tested with different datasets and compared with some existing well known methods. Experimental evaluation clearly proves the robustness and effectiveness of the proposed scheme over similar techniques.

KW - Biometrics

KW - Ear recognition

KW - Neural network

KW - Biometric authentication

KW - Safety and security

UR - http://www.ieeeiciea.org/2017/?utm_source=researchbib

UR - https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8282803

U2 - 10.1109/ICIEA.2017.8283140

DO - 10.1109/ICIEA.2017.8283140

M3 - Conference paper

SP - 1855

EP - 1859

BT - Proceedings of the 2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA)

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States

T2 - 2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA)

Y2 - 18 June 2017 through 20 June 2017

ER -

Robust Ear Biometric Recognition using Neural Network

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this