Geodesic Paths for Image Segmentation with Implicit Region-based Homogeneity Enhancement
Chen, Da; Zhu, Jian; Zhang, Xinxin; Shu, Minglei; Cohen, Laurent D. (2021), Geodesic Paths for Image Segmentation with Implicit Region-based Homogeneity Enhancement, IEEE Transactions on Image Processing, 30, p. 5138 - 5153. 10.1109/TIP.2021.3078106
Type
Article accepté pour publication ou publiéExternal document link
https://arxiv.org/pdf/2008.06909.pdfDate
2021Journal name
IEEE Transactions on Image ProcessingVolume
30Publisher
IEEE - Institute of Electrical and Electronics Engineers
Pages
5138 - 5153
Publication identifier
Metadata
Show full item recordAuthor(s)
Chen, DaShandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250014, China
Zhu, Jian
Shandong First Medical University
Zhang, Xinxin
The Chinese University of Hong Kong
Shu, Minglei
Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250014, China
Cohen, Laurent D.
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Abstract (EN)
Minimal paths are considered as a powerful and efficient tool for boundary detection and image segmentation due to its global optimality and well-established numerical solutions such as fast marching algorithm. In this paper, we introduce a flexible interactive image segmentation model based on the minimal geodesic framework in conjunction with region-based homogeneity enhancement. A key ingredient in our model is the construction of Finsler geodesic metrics, which are capable of integrating anisotropic and asymmetric edge features, region-based homogeneity and/or curvature regularization. This is done by exploiting an implicit method to incorporate the region-based homogeneity information to the metrics used. Moreover, we also introduce a way to build objective simple closed contours, each of which is treated as the concatenation of two disjoint open paths. Experimental results prove that the proposed model indeed outperforms state-of-the-art minimal paths-based image segmentation approaches.Subjects / Keywords
Geodesic path; Eikonal equation; asymmetric Finsler metric; region-based homogeneity; interactive image segmentationRelated items
Showing items related by title and author.
-
Cohen, Laurent D.; Chen, Da; Mirebeau, Jean-Marie; Shu, Minglei; Shu, Huazhong (2021) Document de travail / Working paper
-
Cohen, Laurent D.; Chen, Da; Mirebeau, Jean-Marie; Shu, Ming-Lei; Shu, Huazhong (2021) Document de travail / Working paper
-
Chen, Da; Cohen, Laurent D.; Mirebeau, Jean-Marie; Tai, Xue-Cheng (2021) Communication / Conférence
-
Chen, Da; Spencer, Jack; Mirebeau, Jean-Marie; Chen, Ke; Shu, Minglei; Cohen, Laurent D. (2021) Article accepté pour publication ou publié
-
Cohen, Laurent D. (2016) Communication / Conférence