Improvement of Identity Recognition with Occlusion Detection-Based Feature Selection
Image-based facial identity recognition has become a technology that is now used in many applications. This is because it is possible to use only a camera without the need for any other device. Besides, due to the advantage of contactless technology, it is one of the most popular certifications. How...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-01-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/10/2/167 |
_version_ | 1797411970646802432 |
---|---|
author | Jaeyoon Jang Ho-Sub Yoon Jaehong Kim |
author_facet | Jaeyoon Jang Ho-Sub Yoon Jaehong Kim |
author_sort | Jaeyoon Jang |
collection | DOAJ |
description | Image-based facial identity recognition has become a technology that is now used in many applications. This is because it is possible to use only a camera without the need for any other device. Besides, due to the advantage of contactless technology, it is one of the most popular certifications. However, a common recognition system is not possible if some of the face information is lost due to the user’s posture or the wearing of masks, as caused by the recent prevalent disease. In some platforms, although performance is improved through incremental updates, it is still inconvenient and inaccurate. In this paper, we propose a method to respond more actively to these situations. First, we determine whether an obscurity occurs and improve the stability by calculating the feature vector using only a significant area when the obscurity occurs. By recycling the existing recognition model, without incurring little additional costs, the results of reducing the recognition performance drop in certain situations were confirmed. Using this technique, we confirmed a performance improvement of about 1~3% in a situation where some information is lost. Although the performance is not dramatically improved, it has the big advantage that it can improve recognition performance by utilizing existing systems. |
first_indexed | 2024-03-09T04:54:13Z |
format | Article |
id | doaj.art-8b39c6c560c04b69bce1a6ca53a74428 |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-09T04:54:13Z |
publishDate | 2021-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-8b39c6c560c04b69bce1a6ca53a744282023-12-03T13:07:21ZengMDPI AGElectronics2079-92922021-01-0110216710.3390/electronics10020167Improvement of Identity Recognition with Occlusion Detection-Based Feature SelectionJaeyoon Jang0Ho-Sub Yoon1Jaehong Kim2Electronics and Telecommunications Research Institute (ETRI), Daejeon 34129, KoreaElectronics and Telecommunications Research Institute (ETRI), Daejeon 34129, KoreaElectronics and Telecommunications Research Institute (ETRI), Daejeon 34129, KoreaImage-based facial identity recognition has become a technology that is now used in many applications. This is because it is possible to use only a camera without the need for any other device. Besides, due to the advantage of contactless technology, it is one of the most popular certifications. However, a common recognition system is not possible if some of the face information is lost due to the user’s posture or the wearing of masks, as caused by the recent prevalent disease. In some platforms, although performance is improved through incremental updates, it is still inconvenient and inaccurate. In this paper, we propose a method to respond more actively to these situations. First, we determine whether an obscurity occurs and improve the stability by calculating the feature vector using only a significant area when the obscurity occurs. By recycling the existing recognition model, without incurring little additional costs, the results of reducing the recognition performance drop in certain situations were confirmed. Using this technique, we confirmed a performance improvement of about 1~3% in a situation where some information is lost. Although the performance is not dramatically improved, it has the big advantage that it can improve recognition performance by utilizing existing systems.https://www.mdpi.com/2079-9292/10/2/167face verificationocclusion detectionfeature selection |
spellingShingle | Jaeyoon Jang Ho-Sub Yoon Jaehong Kim Improvement of Identity Recognition with Occlusion Detection-Based Feature Selection Electronics face verification occlusion detection feature selection |
title | Improvement of Identity Recognition with Occlusion Detection-Based Feature Selection |
title_full | Improvement of Identity Recognition with Occlusion Detection-Based Feature Selection |
title_fullStr | Improvement of Identity Recognition with Occlusion Detection-Based Feature Selection |
title_full_unstemmed | Improvement of Identity Recognition with Occlusion Detection-Based Feature Selection |
title_short | Improvement of Identity Recognition with Occlusion Detection-Based Feature Selection |
title_sort | improvement of identity recognition with occlusion detection based feature selection |
topic | face verification occlusion detection feature selection |
url | https://www.mdpi.com/2079-9292/10/2/167 |
work_keys_str_mv | AT jaeyoonjang improvementofidentityrecognitionwithocclusiondetectionbasedfeatureselection AT hosubyoon improvementofidentityrecognitionwithocclusiondetectionbasedfeatureselection AT jaehongkim improvementofidentityrecognitionwithocclusiondetectionbasedfeatureselection |