Border Control by Multi-biometric Identification using Face and Ear images

Susara S. Thenuwara, Chinthaka Premachandra, Hiroharu Kawanaka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Biometrics are critical authorization method in border control areas such as airports. This study explores the usage of the ear and face biometric for verification at the physical appearance of the border points and indicates experimental results collected on a newly made database containing four hundred and twenty images. The images have been taken through a quality module for the purpose of reducing the False Rejection Rate. The approach that was used is The Principal Component Analysis (PCA) that is 'eigen ear' for obtaining the recognition rate of 89.3%. After the ear was fused with face biometric, there was an improvement in the recognition. The fusion is done at the level of decision making, hitting a recognition of 97.1%, which is an improvement of 8.2%.

Original languageEnglish
Title of host publication2022 2nd International Conference on Image Processing and Robotics, ICIPRob 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665407717
DOIs
Publication statusPublished - 2022
Event2nd International Conference on Image Processing and Robotics, ICIPRob 2022 - Colombo, Sri Lanka
Duration: 2022 Mar 122022 Mar 13

Publication series

Name2022 2nd International Conference on Image Processing and Robotics, ICIPRob 2022

Conference

Conference2nd International Conference on Image Processing and Robotics, ICIPRob 2022
Country/TerritorySri Lanka
CityColombo
Period22/3/1222/3/13

Keywords

  • Biometric authentication
  • border control
  • image processing

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Control and Optimization
  • Modelling and Simulation

Fingerprint

Dive into the research topics of 'Border Control by Multi-biometric Identification using Face and Ear images'. Together they form a unique fingerprint.

Cite this