Convolutional Neural Network-Based Periocular Recognition in Surveillance Environments
Visible light surveillance cameras are currently deployed on a large scale to prevent crime and accidents in public urban environments. For this reason, various human identification studies using biometric data are underway in surveillance environments. The most active research area is face recognit...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2018-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8482116/ |
id |
doaj-14b3064385a54c0a870fd9ebe9703411 |
---|---|
record_format |
Article |
spelling |
doaj-14b3064385a54c0a870fd9ebe97034112021-03-29T21:31:49ZengIEEEIEEE Access2169-35362018-01-016572915731010.1109/ACCESS.2018.28740568482116Convolutional Neural Network-Based Periocular Recognition in Surveillance EnvironmentsMin Cheol Kim0Ja Hyung Koo1Se Woon Cho2Na Rae Baek3Kang Ryoung Park4https://orcid.org/0000-0002-1214-9510Division of Electronics and Electrical Engineering, Dongguk University, Seoul, South KoreaDivision of Electronics and Electrical Engineering, Dongguk University, Seoul, South KoreaDivision of Electronics and Electrical Engineering, Dongguk University, Seoul, South KoreaDivision of Electronics and Electrical Engineering, Dongguk University, Seoul, South KoreaDivision of Electronics and Electrical Engineering, Dongguk University, Seoul, South KoreaVisible light surveillance cameras are currently deployed on a large scale to prevent crime and accidents in public urban environments. For this reason, various human identification studies using biometric data are underway in surveillance environments. The most active research area is face recognition, which generally shows excellent performance; however, aging, changes in facial expression, and occlusions by accessories cause a rapid decline in recognition performance. To resolve these problems, we propose a periocular recognition method in surveillance environments that is based on the convolutional neural network. In this paper, experiments were performed using the custom-made Dongguk periocular database and the open database of ChokePoint database. It was confirmed that the proposed method performs better than existing techniques used in periocular recognition. It was also found to perform better than conventional techniques in face recognition when an occlusion is present.https://ieeexplore.ieee.org/document/8482116/Visible light surveillance camera sensorbiometricsperiocular recognitionCNN |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Min Cheol Kim Ja Hyung Koo Se Woon Cho Na Rae Baek Kang Ryoung Park |
spellingShingle |
Min Cheol Kim Ja Hyung Koo Se Woon Cho Na Rae Baek Kang Ryoung Park Convolutional Neural Network-Based Periocular Recognition in Surveillance Environments IEEE Access Visible light surveillance camera sensor biometrics periocular recognition CNN |
author_facet |
Min Cheol Kim Ja Hyung Koo Se Woon Cho Na Rae Baek Kang Ryoung Park |
author_sort |
Min Cheol Kim |
title |
Convolutional Neural Network-Based Periocular Recognition in Surveillance Environments |
title_short |
Convolutional Neural Network-Based Periocular Recognition in Surveillance Environments |
title_full |
Convolutional Neural Network-Based Periocular Recognition in Surveillance Environments |
title_fullStr |
Convolutional Neural Network-Based Periocular Recognition in Surveillance Environments |
title_full_unstemmed |
Convolutional Neural Network-Based Periocular Recognition in Surveillance Environments |
title_sort |
convolutional neural network-based periocular recognition in surveillance environments |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2018-01-01 |
description |
Visible light surveillance cameras are currently deployed on a large scale to prevent crime and accidents in public urban environments. For this reason, various human identification studies using biometric data are underway in surveillance environments. The most active research area is face recognition, which generally shows excellent performance; however, aging, changes in facial expression, and occlusions by accessories cause a rapid decline in recognition performance. To resolve these problems, we propose a periocular recognition method in surveillance environments that is based on the convolutional neural network. In this paper, experiments were performed using the custom-made Dongguk periocular database and the open database of ChokePoint database. It was confirmed that the proposed method performs better than existing techniques used in periocular recognition. It was also found to perform better than conventional techniques in face recognition when an occlusion is present. |
topic |
Visible light surveillance camera sensor biometrics periocular recognition CNN |
url |
https://ieeexplore.ieee.org/document/8482116/ |
work_keys_str_mv |
AT mincheolkim convolutionalneuralnetworkbasedperiocularrecognitioninsurveillanceenvironments AT jahyungkoo convolutionalneuralnetworkbasedperiocularrecognitioninsurveillanceenvironments AT sewooncho convolutionalneuralnetworkbasedperiocularrecognitioninsurveillanceenvironments AT naraebaek convolutionalneuralnetworkbasedperiocularrecognitioninsurveillanceenvironments AT kangryoungpark convolutionalneuralnetworkbasedperiocularrecognitioninsurveillanceenvironments |
_version_ |
1724192726378872832 |