A Novel DenseNet Generative Adversarial Network for Heterogenous Low-Light Image Enhancement
With the development of computer vision, high quality images with rich information have great research potential in both daily life and scientific research. However, due to different lighting conditions, surrounding noise and other reasons, the image quality is different, which seriously affects peo...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-06-01
|
| Series: | Frontiers in Neurorobotics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnbot.2021.700011/full |
| _version_ | 1818743689003925504 |
|---|---|
| author | Jingsi Zhang Chengdong Wu Xiaosheng Yu Xiaoliang Lei |
| author_facet | Jingsi Zhang Chengdong Wu Xiaosheng Yu Xiaoliang Lei |
| author_sort | Jingsi Zhang |
| collection | DOAJ |
| description | With the development of computer vision, high quality images with rich information have great research potential in both daily life and scientific research. However, due to different lighting conditions, surrounding noise and other reasons, the image quality is different, which seriously affects people's discrimination of the information in the image, thus causing unnecessary conflicts and results. Especially in the dark, the images captured by the camera are difficult to identify, and the smart system relies heavily on high-quality input images. The image collected in low-light environment has the characteristic with high noise and color distortion, which makes it difficult to utilize the image and can not fully explore the rich value information of the image. In order to improve the quality of low-light image, this paper proposes a Heterogenous low-light image enhancement method based on DenseNet generative adversarial network. Firstly, the generative network of generative adversarial network is realized by using DenseNet framework. Secondly, the feature map from low light image to normal light image is learned by using the generative adversarial network. Thirdly, the enhancement of low-light image is realized. The experimental results show that, in terms of PSNR, SSIM, NIQE, UQI, NQE and PIQE indexes, compared with the state-of-the-art enhancement algorithms, the values are ideal, the proposed method can improve the image brightness more effectively and reduce the noise of enhanced image. |
| first_indexed | 2024-12-18T02:32:24Z |
| format | Article |
| id | doaj.art-055d164b7ef84616a9440cc82c142c26 |
| institution | Directory Open Access Journal |
| issn | 1662-5218 |
| language | English |
| last_indexed | 2024-12-18T02:32:24Z |
| publishDate | 2021-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurorobotics |
| spelling | doaj.art-055d164b7ef84616a9440cc82c142c262022-12-21T21:23:52ZengFrontiers Media S.A.Frontiers in Neurorobotics1662-52182021-06-011510.3389/fnbot.2021.700011700011A Novel DenseNet Generative Adversarial Network for Heterogenous Low-Light Image EnhancementJingsi ZhangChengdong WuXiaosheng YuXiaoliang LeiWith the development of computer vision, high quality images with rich information have great research potential in both daily life and scientific research. However, due to different lighting conditions, surrounding noise and other reasons, the image quality is different, which seriously affects people's discrimination of the information in the image, thus causing unnecessary conflicts and results. Especially in the dark, the images captured by the camera are difficult to identify, and the smart system relies heavily on high-quality input images. The image collected in low-light environment has the characteristic with high noise and color distortion, which makes it difficult to utilize the image and can not fully explore the rich value information of the image. In order to improve the quality of low-light image, this paper proposes a Heterogenous low-light image enhancement method based on DenseNet generative adversarial network. Firstly, the generative network of generative adversarial network is realized by using DenseNet framework. Secondly, the feature map from low light image to normal light image is learned by using the generative adversarial network. Thirdly, the enhancement of low-light image is realized. The experimental results show that, in terms of PSNR, SSIM, NIQE, UQI, NQE and PIQE indexes, compared with the state-of-the-art enhancement algorithms, the values are ideal, the proposed method can improve the image brightness more effectively and reduce the noise of enhanced image.https://www.frontiersin.org/articles/10.3389/fnbot.2021.700011/fullDenseNet frameworkgenerative adversarial networkimage enhancementheterogenous low-light imagefeature map |
| spellingShingle | Jingsi Zhang Chengdong Wu Xiaosheng Yu Xiaoliang Lei A Novel DenseNet Generative Adversarial Network for Heterogenous Low-Light Image Enhancement Frontiers in Neurorobotics DenseNet framework generative adversarial network image enhancement heterogenous low-light image feature map |
| title | A Novel DenseNet Generative Adversarial Network for Heterogenous Low-Light Image Enhancement |
| title_full | A Novel DenseNet Generative Adversarial Network for Heterogenous Low-Light Image Enhancement |
| title_fullStr | A Novel DenseNet Generative Adversarial Network for Heterogenous Low-Light Image Enhancement |
| title_full_unstemmed | A Novel DenseNet Generative Adversarial Network for Heterogenous Low-Light Image Enhancement |
| title_short | A Novel DenseNet Generative Adversarial Network for Heterogenous Low-Light Image Enhancement |
| title_sort | novel densenet generative adversarial network for heterogenous low light image enhancement |
| topic | DenseNet framework generative adversarial network image enhancement heterogenous low-light image feature map |
| url | https://www.frontiersin.org/articles/10.3389/fnbot.2021.700011/full |
| work_keys_str_mv | AT jingsizhang anoveldensenetgenerativeadversarialnetworkforheterogenouslowlightimageenhancement AT chengdongwu anoveldensenetgenerativeadversarialnetworkforheterogenouslowlightimageenhancement AT xiaoshengyu anoveldensenetgenerativeadversarialnetworkforheterogenouslowlightimageenhancement AT xiaolianglei anoveldensenetgenerativeadversarialnetworkforheterogenouslowlightimageenhancement AT jingsizhang noveldensenetgenerativeadversarialnetworkforheterogenouslowlightimageenhancement AT chengdongwu noveldensenetgenerativeadversarialnetworkforheterogenouslowlightimageenhancement AT xiaoshengyu noveldensenetgenerativeadversarialnetworkforheterogenouslowlightimageenhancement AT xiaolianglei noveldensenetgenerativeadversarialnetworkforheterogenouslowlightimageenhancement |