Multimodal Human Recognition in Significantly Low Illumination Environment Using Modified EnlightenGAN
Human recognition in indoor environments occurs both during the day and at night. During the day, human recognition encounters performance degradation owing to a blur generated when a camera captures a person’s image. However, when images are captured at night with a camera, it is difficult to obtai...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/9/16/1934 |
| _version_ | 1797522996971175936 |
|---|---|
| author | Ja Hyung Koo Se Woon Cho Na Rae Baek Kang Ryoung Park |
| author_facet | Ja Hyung Koo Se Woon Cho Na Rae Baek Kang Ryoung Park |
| author_sort | Ja Hyung Koo |
| collection | DOAJ |
| description | Human recognition in indoor environments occurs both during the day and at night. During the day, human recognition encounters performance degradation owing to a blur generated when a camera captures a person’s image. However, when images are captured at night with a camera, it is difficult to obtain perfect images of a person without light, and the input images are very noisy owing to the properties of camera sensors in low-illumination environments. Studies have been conducted in the past on face recognition in low-illumination environments; however, there is lack of research on face- and body-based human recognition in very low illumination environments. To solve these problems, this study proposes a modified enlighten generative adversarial network (modified EnlightenGAN) in which a very low illumination image is converted to a normal illumination image, and the matching scores of deep convolutional neural network (CNN) features of the face and body in the converted image are combined with a score-level fusion for recognition. The two types of databases used in this study are the Dongguk face and body database version 3 (DFB-DB3) and the ChokePoint open dataset. The results of the experiment conducted using the two databases show that the human verification accuracy (equal error rate (ERR)) and identification accuracy (rank 1 genuine acceptance rate (GAR)) of the proposed method were 7.291% and 92.67% for DFB-DB3 and 10.59% and 87.78% for the ChokePoint dataset, respectively. Accordingly, the performance of the proposed method was better than the previous methods. |
| first_indexed | 2024-03-10T08:37:14Z |
| format | Article |
| id | doaj.art-8f35c988bf154d8880d51479ad6659d0 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T08:37:14Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-8f35c988bf154d8880d51479ad6659d02023-11-22T08:34:06ZengMDPI AGMathematics2227-73902021-08-01916193410.3390/math9161934Multimodal Human Recognition in Significantly Low Illumination Environment Using Modified EnlightenGANJa Hyung Koo0Se Woon Cho1Na Rae Baek2Kang Ryoung Park3Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, KoreaDivision of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, KoreaDivision of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, KoreaDivision of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, KoreaHuman recognition in indoor environments occurs both during the day and at night. During the day, human recognition encounters performance degradation owing to a blur generated when a camera captures a person’s image. However, when images are captured at night with a camera, it is difficult to obtain perfect images of a person without light, and the input images are very noisy owing to the properties of camera sensors in low-illumination environments. Studies have been conducted in the past on face recognition in low-illumination environments; however, there is lack of research on face- and body-based human recognition in very low illumination environments. To solve these problems, this study proposes a modified enlighten generative adversarial network (modified EnlightenGAN) in which a very low illumination image is converted to a normal illumination image, and the matching scores of deep convolutional neural network (CNN) features of the face and body in the converted image are combined with a score-level fusion for recognition. The two types of databases used in this study are the Dongguk face and body database version 3 (DFB-DB3) and the ChokePoint open dataset. The results of the experiment conducted using the two databases show that the human verification accuracy (equal error rate (ERR)) and identification accuracy (rank 1 genuine acceptance rate (GAR)) of the proposed method were 7.291% and 92.67% for DFB-DB3 and 10.59% and 87.78% for the ChokePoint dataset, respectively. Accordingly, the performance of the proposed method was better than the previous methods.https://www.mdpi.com/2227-7390/9/16/1934multimodal human recognitionvery low illumination environmentimage enhancementmodified EnlightenGANCNN |
| spellingShingle | Ja Hyung Koo Se Woon Cho Na Rae Baek Kang Ryoung Park Multimodal Human Recognition in Significantly Low Illumination Environment Using Modified EnlightenGAN Mathematics multimodal human recognition very low illumination environment image enhancement modified EnlightenGAN CNN |
| title | Multimodal Human Recognition in Significantly Low Illumination Environment Using Modified EnlightenGAN |
| title_full | Multimodal Human Recognition in Significantly Low Illumination Environment Using Modified EnlightenGAN |
| title_fullStr | Multimodal Human Recognition in Significantly Low Illumination Environment Using Modified EnlightenGAN |
| title_full_unstemmed | Multimodal Human Recognition in Significantly Low Illumination Environment Using Modified EnlightenGAN |
| title_short | Multimodal Human Recognition in Significantly Low Illumination Environment Using Modified EnlightenGAN |
| title_sort | multimodal human recognition in significantly low illumination environment using modified enlightengan |
| topic | multimodal human recognition very low illumination environment image enhancement modified EnlightenGAN CNN |
| url | https://www.mdpi.com/2227-7390/9/16/1934 |
| work_keys_str_mv | AT jahyungkoo multimodalhumanrecognitioninsignificantlylowilluminationenvironmentusingmodifiedenlightengan AT sewooncho multimodalhumanrecognitioninsignificantlylowilluminationenvironmentusingmodifiedenlightengan AT naraebaek multimodalhumanrecognitioninsignificantlylowilluminationenvironmentusingmodifiedenlightengan AT kangryoungpark multimodalhumanrecognitioninsignificantlylowilluminationenvironmentusingmodifiedenlightengan |