Deep learning-based prediction of multi-level just noticeable distortion
Visual just noticeable distortion (JND) directly reflects the sensitivity of the human visual system to visual signal noise, and is widely used in image and video processing.Aiming at the multilevel prediction problem of video JND threshold, it was transformed into the prediction problem of satisfie...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2024-01-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2024015/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533660476473344 |
|---|---|
| author | Haifeng XU Hongkui WANG Haibing YIN Chuqiao CHEN |
| author_facet | Haifeng XU Hongkui WANG Haibing YIN Chuqiao CHEN |
| author_sort | Haifeng XU |
| collection | DOAJ |
| description | Visual just noticeable distortion (JND) directly reflects the sensitivity of the human visual system to visual signal noise, and is widely used in image and video processing.Aiming at the multilevel prediction problem of video JND threshold, it was transformed into the prediction problem of satisfied user ratio (SUR) curve, and a feature fusion-based SUR curve prediction model was proposed.The model was mainly divided into key frame extraction module, feature extraction and fusion module, and SUR score regression module.In the key frame extraction module, according to the visual perception mechanism, the spatial-temporal domain perception complexity was proposed and used as the video key frame judgment index.In the feature extraction and fusion module, a multi-scale dense residual network was proposed based on dense residual block (RDB) to realize image feature extraction and multi-scale fusion.The experimental results show that the proposed SUR curve prediction model is overall better than the existing models in terms of JND prediction accuracy and reduces the time cost by 8.1% on average in terms of operational efficiency.Meanwhile, the model can also be used to predict other layers of JND thresholds, which can be directly applied to video multilevel perceptual coding optimization. |
| format | Article |
| id | doaj-art-ac822c36f43e4a84a579f164970e0f1d |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2024-01-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-ac822c36f43e4a84a579f164970e0f1d2025-01-15T02:57:29ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012024-01-0140354759556866Deep learning-based prediction of multi-level just noticeable distortionHaifeng XUHongkui WANGHaibing YINChuqiao CHENVisual just noticeable distortion (JND) directly reflects the sensitivity of the human visual system to visual signal noise, and is widely used in image and video processing.Aiming at the multilevel prediction problem of video JND threshold, it was transformed into the prediction problem of satisfied user ratio (SUR) curve, and a feature fusion-based SUR curve prediction model was proposed.The model was mainly divided into key frame extraction module, feature extraction and fusion module, and SUR score regression module.In the key frame extraction module, according to the visual perception mechanism, the spatial-temporal domain perception complexity was proposed and used as the video key frame judgment index.In the feature extraction and fusion module, a multi-scale dense residual network was proposed based on dense residual block (RDB) to realize image feature extraction and multi-scale fusion.The experimental results show that the proposed SUR curve prediction model is overall better than the existing models in terms of JND prediction accuracy and reduces the time cost by 8.1% on average in terms of operational efficiency.Meanwhile, the model can also be used to predict other layers of JND thresholds, which can be directly applied to video multilevel perceptual coding optimization.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2024015/just noticeable distortiondeep learningquality evaluation |
| spellingShingle | Haifeng XU Hongkui WANG Haibing YIN Chuqiao CHEN Deep learning-based prediction of multi-level just noticeable distortion Dianxin kexue just noticeable distortion deep learning quality evaluation |
| title | Deep learning-based prediction of multi-level just noticeable distortion |
| title_full | Deep learning-based prediction of multi-level just noticeable distortion |
| title_fullStr | Deep learning-based prediction of multi-level just noticeable distortion |
| title_full_unstemmed | Deep learning-based prediction of multi-level just noticeable distortion |
| title_short | Deep learning-based prediction of multi-level just noticeable distortion |
| title_sort | deep learning based prediction of multi level just noticeable distortion |
| topic | just noticeable distortion deep learning quality evaluation |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2024015/ |
| work_keys_str_mv | AT haifengxu deeplearningbasedpredictionofmultileveljustnoticeabledistortion AT hongkuiwang deeplearningbasedpredictionofmultileveljustnoticeabledistortion AT haibingyin deeplearningbasedpredictionofmultileveljustnoticeabledistortion AT chuqiaochen deeplearningbasedpredictionofmultileveljustnoticeabledistortion |