Image Semantic Segmentation Use Multiple-Threshold Probabilistic R-CNN with Feature Fusion
With continuous developments in deep learning, image semantic segmentation technology has also undergone great advancements and been widely used in many fields with higher segmentation accuracy. This paper proposes an image semantic segmentation algorithm based on a deep neural network. Based on the...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/13/2/207 |
| _version_ | 1797406597909053440 |
|---|---|
| author | Jianxin Liu Yushui Geng Jing Zhao Kang Zhang Wenxiao Li |
| author_facet | Jianxin Liu Yushui Geng Jing Zhao Kang Zhang Wenxiao Li |
| author_sort | Jianxin Liu |
| collection | DOAJ |
| description | With continuous developments in deep learning, image semantic segmentation technology has also undergone great advancements and been widely used in many fields with higher segmentation accuracy. This paper proposes an image semantic segmentation algorithm based on a deep neural network. Based on the Mask Scoring R-CNN, this algorithm uses a symmetrical feature pyramid network and adds a multiple-threshold architecture to improve the sample screening precision. We employ a probability model to optimize the mask branch of the model further to improve the algorithm accuracy for the segmentation of image edges. In addition, we adjust the loss function so that the experimental effect can be optimized. The experiments reveal that the algorithm improves the results. |
| first_indexed | 2024-03-09T03:28:50Z |
| format | Article |
| id | doaj.art-bbd76a4e56d04401a0468b2d07a481bc |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-09T03:28:50Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-bbd76a4e56d04401a0468b2d07a481bc2023-12-03T14:59:03ZengMDPI AGSymmetry2073-89942021-01-0113220710.3390/sym13020207Image Semantic Segmentation Use Multiple-Threshold Probabilistic R-CNN with Feature FusionJianxin Liu0Yushui Geng1Jing Zhao2Kang Zhang3Wenxiao Li4School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaWith continuous developments in deep learning, image semantic segmentation technology has also undergone great advancements and been widely used in many fields with higher segmentation accuracy. This paper proposes an image semantic segmentation algorithm based on a deep neural network. Based on the Mask Scoring R-CNN, this algorithm uses a symmetrical feature pyramid network and adds a multiple-threshold architecture to improve the sample screening precision. We employ a probability model to optimize the mask branch of the model further to improve the algorithm accuracy for the segmentation of image edges. In addition, we adjust the loss function so that the experimental effect can be optimized. The experiments reveal that the algorithm improves the results.https://www.mdpi.com/2073-8994/13/2/207deep learningimage semantic segmentationmultiple threshold |
| spellingShingle | Jianxin Liu Yushui Geng Jing Zhao Kang Zhang Wenxiao Li Image Semantic Segmentation Use Multiple-Threshold Probabilistic R-CNN with Feature Fusion Symmetry deep learning image semantic segmentation multiple threshold |
| title | Image Semantic Segmentation Use Multiple-Threshold Probabilistic R-CNN with Feature Fusion |
| title_full | Image Semantic Segmentation Use Multiple-Threshold Probabilistic R-CNN with Feature Fusion |
| title_fullStr | Image Semantic Segmentation Use Multiple-Threshold Probabilistic R-CNN with Feature Fusion |
| title_full_unstemmed | Image Semantic Segmentation Use Multiple-Threshold Probabilistic R-CNN with Feature Fusion |
| title_short | Image Semantic Segmentation Use Multiple-Threshold Probabilistic R-CNN with Feature Fusion |
| title_sort | image semantic segmentation use multiple threshold probabilistic r cnn with feature fusion |
| topic | deep learning image semantic segmentation multiple threshold |
| url | https://www.mdpi.com/2073-8994/13/2/207 |
| work_keys_str_mv | AT jianxinliu imagesemanticsegmentationusemultiplethresholdprobabilisticrcnnwithfeaturefusion AT yushuigeng imagesemanticsegmentationusemultiplethresholdprobabilisticrcnnwithfeaturefusion AT jingzhao imagesemanticsegmentationusemultiplethresholdprobabilisticrcnnwithfeaturefusion AT kangzhang imagesemanticsegmentationusemultiplethresholdprobabilisticrcnnwithfeaturefusion AT wenxiaoli imagesemanticsegmentationusemultiplethresholdprobabilisticrcnnwithfeaturefusion |