NIR Reflection Augmentation for DeepLearning-Based NIR Face Recognition
Face recognition using a near-infrared (NIR) sensor is widely applied to practical applications such as mobile unlocking or access control. However, unlike RGB sensors, few deep learning approaches have studied NIR face recognition. We conducted comparative experiments for the application of deep le...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-10-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/11/10/1234 |
| _version_ | 1798005604310056960 |
|---|---|
| author | Hoon Jo Whoi-Yul Kim |
| author_facet | Hoon Jo Whoi-Yul Kim |
| author_sort | Hoon Jo |
| collection | DOAJ |
| description | Face recognition using a near-infrared (NIR) sensor is widely applied to practical applications such as mobile unlocking or access control. However, unlike RGB sensors, few deep learning approaches have studied NIR face recognition. We conducted comparative experiments for the application of deep learning to NIR face recognition. To accomplish this, we gathered five public databases and trained two deep learning architectures. In our experiments, we found that simple architecture could have a competitive performance on the NIR face databases that are mostly composed of frontal face images. Furthermore, we propose a data augmentation method to train the architectures to improve recognition of users who wear glasses. With this augmented training set, the recognition rate for users who wear glasses increased by up to 16%. This result implies that the recognition of those who wear glasses can be overcome using this simple method without constructing an additional training set. Furthermore, the model that uses augmented data has symmetry with those trained with real glasses-wearing data regarding the recognition of people who wear glasses. |
| first_indexed | 2024-04-11T12:41:52Z |
| format | Article |
| id | doaj.art-4fede9e9f9a743348df32f41b15cefc5 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-04-11T12:41:52Z |
| publishDate | 2019-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-4fede9e9f9a743348df32f41b15cefc52022-12-22T04:23:28ZengMDPI AGSymmetry2073-89942019-10-011110123410.3390/sym11101234sym11101234NIR Reflection Augmentation for DeepLearning-Based NIR Face RecognitionHoon Jo0Whoi-Yul Kim1Department of Electronics and Computer Engineering, Hanyang University, Seoul 04763, KoreaDepartment of Electronics and Computer Engineering, Hanyang University, Seoul 04763, KoreaFace recognition using a near-infrared (NIR) sensor is widely applied to practical applications such as mobile unlocking or access control. However, unlike RGB sensors, few deep learning approaches have studied NIR face recognition. We conducted comparative experiments for the application of deep learning to NIR face recognition. To accomplish this, we gathered five public databases and trained two deep learning architectures. In our experiments, we found that simple architecture could have a competitive performance on the NIR face databases that are mostly composed of frontal face images. Furthermore, we propose a data augmentation method to train the architectures to improve recognition of users who wear glasses. With this augmented training set, the recognition rate for users who wear glasses increased by up to 16%. This result implies that the recognition of those who wear glasses can be overcome using this simple method without constructing an additional training set. Furthermore, the model that uses augmented data has symmetry with those trained with real glasses-wearing data regarding the recognition of people who wear glasses.https://www.mdpi.com/2073-8994/11/10/1234face recognitiondeep learningdata augmentationnear-infrared image |
| spellingShingle | Hoon Jo Whoi-Yul Kim NIR Reflection Augmentation for DeepLearning-Based NIR Face Recognition Symmetry face recognition deep learning data augmentation near-infrared image |
| title | NIR Reflection Augmentation for DeepLearning-Based NIR Face Recognition |
| title_full | NIR Reflection Augmentation for DeepLearning-Based NIR Face Recognition |
| title_fullStr | NIR Reflection Augmentation for DeepLearning-Based NIR Face Recognition |
| title_full_unstemmed | NIR Reflection Augmentation for DeepLearning-Based NIR Face Recognition |
| title_short | NIR Reflection Augmentation for DeepLearning-Based NIR Face Recognition |
| title_sort | nir reflection augmentation for deeplearning based nir face recognition |
| topic | face recognition deep learning data augmentation near-infrared image |
| url | https://www.mdpi.com/2073-8994/11/10/1234 |
| work_keys_str_mv | AT hoonjo nirreflectionaugmentationfordeeplearningbasednirfacerecognition AT whoiyulkim nirreflectionaugmentationfordeeplearningbasednirfacerecognition |