Biometric authentication using facial recognition

Mohammad Mozammel Hoque Chowdhury, Junbin Gao, MD Rafiqul Islam

Research output: Book chapter/Published conference paperConference paperpeer-review

4 Citations (Scopus)


Biometric authentication has been gaining popularity for providing privacy and security in many applications including secure access control, surveillance systems, user identification and many more. This research proposes a robust scheme for biometric authentication by analyzing and interpreting facial image using a neural network. Human face has become as the key attribute for biometric authentication over the recent years due to its uniqueness and robustness. Our system focuses on efficient detection and recognition of user’s face for precise authentication. The facial features of a user are compared with a face database in order to perform matching for authentication and authorization. The proposed system estimates the face by analyzing skin color components in the facial image. The facial edge features are then extracted from the detected face skeleton. A neural network is employed and trained with the extracted edge features to recognize the user face by comparing with the facial database. Once the user is identified, authentication is granted. Experimental evaluation demonstrates that our proposed system provides better performance meeting accuracy requirements and less computation time.
Original languageEnglish
Title of host publicationSecurity and privacy in communication networks
Subtitle of host publication12th International Conference, SecureComm 2016, Guangzhou, China, October 10-12, 2016, Proceedings
EditorsRobert Deng, Jian Weng, Kui Ren, Vinod Yegneswaran
Place of PublicationCham, Switzerland
Number of pages9
ISBN (Electronic)9783319596082
ISBN (Print)9783319596075
Publication statusPublished - 2017
Event12th International Conference on Security and Privacy in Communication Networks: SecureComm 2016 - Vanburgh Hotel, Guangzhou, China
Duration: 10 Oct 201612 Oct 2016

Publication series

NameLecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
Volume198 LNICST
ISSN (Print)1867-8211


Conference12th International Conference on Security and Privacy in Communication Networks
Internet address


Dive into the research topics of 'Biometric authentication using facial recognition'. Together they form a unique fingerprint.

Cite this