지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 저널정보
- Korean Institute of Information Scientists and Engineers Journal of Computing Science and Engineering Journal of Computing Science and Engineering Vol.18 No.2
- 발행연도
- 2024.6
- 수록면
- 93 - 115 (23page)
- DOI
- 10.5626/JCSE.2024.18.2.93
이용수
초록· 키워드
오류제보하기
At present, automatic image matting methods primarily focus on portraits and hard edge targets, which gives them a limited ability to deal with low-resolution, complex, and blurred non-portrait targets. To address these issues, the current paper proposes an automatic image matting method called TGMatting. This method automatically optimizes Trimap generation through three modules: the U²S-Net pre-segmentation module, which is based on the U²-Net network, enhances segmentation by removing null convolutions and reducing oversampling interference; the BGTrimap module, which is also based on U²-Net, refines edge regions using optimized dilation-erosion methods and Manhattan distance for seed point sparsification, thus ensuring accurate region growth and background information removal; and in the last module, edges are transformed into mixed-pixel regions using Sobel operator and non-local-means denoising binarization, and a Trimap map is automatically generated by combining OTSU segmentation with pre-segmentation results, thus achieving fully automated processing. Finally, a transparency mask is obtained via FBAMatting, which enables interaction-
free automatic matting. The experimental results demonstrate that the improved U²S-Net network reduces MAE by 0.003 on the SOD-Spider test set, enhances accurate detection of significant regions in low-resolution images compared to U²S-Net, and reduces BGTrimap"s sum of absolute difference value by about 10% compared to other Trimap generation methods in IFMatting and KNN Matting.
free automatic matting. The experimental results demonstrate that the improved U²S-Net network reduces MAE by 0.003 on the SOD-Spider test set, enhances accurate detection of significant regions in low-resolution images compared to U²S-Net, and reduces BGTrimap"s sum of absolute difference value by about 10% compared to other Trimap generation methods in IFMatting and KNN Matting.
목차
Abstract
I. INTRODUCTION
II. TGMATTING AUTOMATIC MATTING METHOD
III. EXPERIMENTAL RESULTS AND ANALYSES
IV. CONCLUSION
REFERENCES
참고문헌 (42)
참고문헌 신청
Y. Liang, H. Huang, Z. Cai, Z. Hao, and F. Feng, “A review of natural image matting techniques,” Application Research of Computers, vol. 38, no. 5, pp. 1294-1301, 2021. https://doi.org/10.19734/j.issn.1001-3695.2020.06.0111
X. Lu and Z. Liu, “A review of image semantic segmentation technology based on deep learning,” Software Guide, vol. 20, no. 1, pp. 242-244, 2021.
C. Shi, W. Zhang, H. Chen, and L. Ge, “Survey of salient object detection based on deep learning,” Journal of Frontiers of Computer Science & Technology, vol. 15, no. 2, pp. 219-232, 2021. https://doi.org/10.3778/j.issn.1673-9418.2007074
N. Xu, B. Price, S. Cohen, and T. Huang, “Deep image matting,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 2017, pp. 2970-2979. https://doi.org/10.1109/CVPR.2017.41
A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, et al., “Segment anything,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, Paris, France, 2023, pp. 4015-4026. https://doi.org/10.1109/ICCV51070.2023.00371
X. Lu and Z. Liu, “A review of image semantic segmentation technology based on deep learning,” Software Guide, vol. 20, no. 1, pp. 242-244, 2021.
C. Shi, W. Zhang, H. Chen, and L. Ge, “Survey of salient object detection based on deep learning,” Journal of Frontiers of Computer Science & Technology, vol. 15, no. 2, pp. 219-232, 2021. https://doi.org/10.3778/j.issn.1673-9418.2007074
N. Xu, B. Price, S. Cohen, and T. Huang, “Deep image matting,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 2017, pp. 2970-2979. https://doi.org/10.1109/CVPR.2017.41
A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, et al., “Segment anything,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, Paris, France, 2023, pp. 4015-4026. https://doi.org/10.1109/ICCV51070.2023.00371
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
ToF 센서를 이용한 Trimap 생성과 전·배경 정합
한국정보과학회 학술발표논문집
2018 .06
-
멀티모달 모델과 이미지 분할 모델을 활용한 지시 기반 이미지 매팅을 위한 Trimap 생성 방법
한국방송미디어공학회 학술발표대회 논문집
2024 .11
-
High-resolution Matting based on Divide-and-Conquer Method with Refined Trimap
한국컴퓨터그래픽스학회 학술대회
2017 .07
-
G-Mat을 활용한 현장 접지설계 기법에 관한 연구
한국조명·전기설비학회 학술대회논문집
2024 .11
-
A Survey on Automatic Natural Image Matting algorithms
한국정보과학회 학술발표논문집
2017 .06
-
A Study on the Development and Management of a New Type of Car Mats
Proceedings of The International Workshop on Future Technology
2017 .07
-
A cux on Transformer-based U-NET models for Medical Image Segmentation
대한전자공학회 학술대회
2024 .06
-
3D analytical method for mat foundations considering coupled soil springs
Geomechanics & engineering
2015 .01
-
고기능성 침낭형 온수매트 제작
전기전자재료학회논문지
2015 .01
-
A Novel User-Friendly Image Analysis Technique for Determination of Electrospun Nanofibrous Mats Thickness
NANO
2017 .01
-
U-Net을 이용한 이미지 내 부식 시편 분할에 관한 연구
한국표면공학회지
2024 .12
-
RDIU-Net: Lightweight Medical Image Segmentation Network
제어로봇시스템학회 국제학술대회 논문집
2023 .10
-
센서 및 방열 소자 개발을 위한 Ag Coated Nanofiber-Mat 연구
한국정밀공학회 학술발표대회 논문집
2017 .12
-
U-Net 기반의 식물 영상 분할 기법
한국정보통신학회 종합학술대회 논문집
2021 .05
-
Simulation of Filter Application for Segmentation of Medical Images
INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING
2018 .06
-
Development of the Smart Mat with IoT Applied Technology
INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGENT SYSTEMS
2019 .12
-
Temporal Difference-based Weighted Instance Segmentation Applied on Consecutive Images for Food Recognition
제어로봇시스템학회 논문지
2023 .12
-
매트-빌딩의 개념을 활용한 건축 디자인 방법 연구 - 프로그램적 활용과 구성을 중심으로 -
대한건축학회 학술발표대회 논문집
2022 .10
-
해양 구조물의 저면매트 수중 포설시 방법 개선에 따른 시공효율 향상 사례
한국지반신소재학회 학술발표회
2015 .10
-
영상 분할을 이용한 영상 전송 시스템에 대한 연구
반도체디스플레이기술학회지
2016 .01
이 논문과 함께 이용한 논문
최근 본 자료
댓글(0)
0