Graph convolutional network‐based image matting algorithm for computer vision applications
Abstract Image matting plays a vital role in a variety of computer vision tasks including video editing and image fusion. Previously presented image matting algorithms might fail in producing favorable results since most of them concentrate on the similarity between the neighboring pixels while negl...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-08-01
|
| Series: | IET Image Processing |
| Online Access: | https://doi.org/10.1049/ipr2.12528 |
| _version_ | 1818467048902098944 |
|---|---|
| author | Li Dong Zheng Liang Yue Wang |
| author_facet | Li Dong Zheng Liang Yue Wang |
| author_sort | Li Dong |
| collection | DOAJ |
| description | Abstract Image matting plays a vital role in a variety of computer vision tasks including video editing and image fusion. Previously presented image matting algorithms might fail in producing favorable results since most of them concentrate on the similarity between the neighboring pixels while neglecting the corresponding spatial relationship. To address this issue, an end‐to‐end image matting framework through leveraging deep learning mechanism and graph theory is proposed. The proposed pipeline is a concatenation of one deep feature extraction component and a Graph Convolutional Network (GCN). The former part takes an image and its corresponding trimap as inputs and can generate the pixel‐wise features, which are then exploited as the input of the GCN locating at the latter part of the proposed framework. The GCN would refine the features for every pixel and predict the alpha matte outcome of the image. The approach outperforms a group of state‐of‐the‐art matting techniques as shown by the theoretical analysis and experimental results in terms of both accuracy and visual effects. |
| first_indexed | 2024-04-13T21:04:28Z |
| format | Article |
| id | doaj.art-3098cb595dd141f8add4bd4197503d3b |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-04-13T21:04:28Z |
| publishDate | 2022-08-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-3098cb595dd141f8add4bd4197503d3b2022-12-22T02:30:01ZengWileyIET Image Processing1751-96591751-96672022-08-0116102817282510.1049/ipr2.12528Graph convolutional network‐based image matting algorithm for computer vision applicationsLi Dong0Zheng Liang1Yue Wang2Department of Social Sciences Shandong Medical College Jinan Shandong Province ChinaDepartment of Social Sciences Shandong Medical College Jinan Shandong Province ChinaDepartment of Social Sciences Shandong Medical College Jinan Shandong Province ChinaAbstract Image matting plays a vital role in a variety of computer vision tasks including video editing and image fusion. Previously presented image matting algorithms might fail in producing favorable results since most of them concentrate on the similarity between the neighboring pixels while neglecting the corresponding spatial relationship. To address this issue, an end‐to‐end image matting framework through leveraging deep learning mechanism and graph theory is proposed. The proposed pipeline is a concatenation of one deep feature extraction component and a Graph Convolutional Network (GCN). The former part takes an image and its corresponding trimap as inputs and can generate the pixel‐wise features, which are then exploited as the input of the GCN locating at the latter part of the proposed framework. The GCN would refine the features for every pixel and predict the alpha matte outcome of the image. The approach outperforms a group of state‐of‐the‐art matting techniques as shown by the theoretical analysis and experimental results in terms of both accuracy and visual effects.https://doi.org/10.1049/ipr2.12528 |
| spellingShingle | Li Dong Zheng Liang Yue Wang Graph convolutional network‐based image matting algorithm for computer vision applications IET Image Processing |
| title | Graph convolutional network‐based image matting algorithm for computer vision applications |
| title_full | Graph convolutional network‐based image matting algorithm for computer vision applications |
| title_fullStr | Graph convolutional network‐based image matting algorithm for computer vision applications |
| title_full_unstemmed | Graph convolutional network‐based image matting algorithm for computer vision applications |
| title_short | Graph convolutional network‐based image matting algorithm for computer vision applications |
| title_sort | graph convolutional network based image matting algorithm for computer vision applications |
| url | https://doi.org/10.1049/ipr2.12528 |
| work_keys_str_mv | AT lidong graphconvolutionalnetworkbasedimagemattingalgorithmforcomputervisionapplications AT zhengliang graphconvolutionalnetworkbasedimagemattingalgorithmforcomputervisionapplications AT yuewang graphconvolutionalnetworkbasedimagemattingalgorithmforcomputervisionapplications |