Academic Journal
Image segmentation using active contours with image structure adaptive gradient vector flow external force
| العنوان: | Image segmentation using active contours with image structure adaptive gradient vector flow external force |
|---|---|
| المؤلفون: | Dong Wang, Xing Dang, Weijing Liu, Yuanquan Wang |
| المصدر: | Frontiers in Applied Mathematics and Statistics, Vol 9 (2023) |
| بيانات النشر: | Frontiers Media S.A., 2023. |
| سنة النشر: | 2023 |
| المجموعة: | LCC:Applied mathematics. Quantitative methods LCC:Probabilities. Mathematical statistics |
| مصطلحات موضوعية: | image segmentation, active contour, gradient vector flow, image structure tensor, diffusion tensor, Applied mathematics. Quantitative methods, T57-57.97, Probabilities. Mathematical statistics, QA273-280 |
| الوصف: | IntroductionGradient vector flow (GVF) has been proven as an effective external force for active contours. However, its smoothness constraint does not take the image structure into account, such that the GVF diffusion is isotropic and cannot preserve weak edges well.MethodsIn this article, an image structure adaptive gradient vector flow (ISAGVF) external force is proposed for active contours. In the proposed ISAGVF model, the smoothness constraint is first reformulated in matrix form, and then the image structure tensor is incorporated. As the structure tensor characterizes the image structure well, the proposed ISAGVF model can be adaptive to image structure, and the ISAGVF snake performs well on weak edge preservation and deep concavity convergence while possessing some other desirable properties of the GVF snake, such as enlarged capture range and insensitivity to initialization.ResultsExperiments on synthetic and real images manifest these properties of the ISAGVF snake. |
| نوع الوثيقة: | article |
| وصف الملف: | electronic resource |
| اللغة: | English |
| تدمد: | 2297-4687 |
| Relation: | https://www.frontiersin.org/articles/10.3389/fams.2023.1271296/full; https://doaj.org/toc/2297-4687 |
| DOI: | 10.3389/fams.2023.1271296 |
| URL الوصول: | https://doaj.org/article/8dd2cdd15f3b48c881a5ae2e5fc327d4 |
| رقم الانضمام: | edsdoj.8dd2cdd15f3b48c881a5ae2e5fc327d4 |
| قاعدة البيانات: | Directory of Open Access Journals |
Full Text Finder | تدمد: | 22974687 |
|---|---|
| DOI: | 10.3389/fams.2023.1271296 |