@inproceedings{a43260a5ec734b909479228bab660ced,
title = "Locally Enhanced Chan-Vese Model with Anisotropic Mesh Adaptation for Intensity Inhomogeneous Image Segmentation",
abstract = "Chan-Vese (CV) model is a well-known mathematical model for image segmentation; however, it has difficulty handling images with inhomogeneous intensity. Many models have been proposed to address this difficulty. In this paper, we propose a locally enhanced Chan-Vese model (LECV) to successfully segment images with intensity inhomogeneity. We define a new signed pressure force (SPF) function based on the local image information from a triangular mesh representation. The anisotropic mesh representation (AMA representation) of the image also helps improving the computational accuracy and efficiency. Numerical results demonstrate that our proposed LECV model provides better segmentation for images with inhomogeneous intensity than the traditional Chan-Vese model as well as a few commonly used models.",
keywords = "AMA representation, Chan-Vese model, Image segmentation, Inhomogeneous intensity, LECV, SPF function",
author = "Abbas, {Karrar K.} and Xianping Li",
note = "Publisher Copyright: {\textcopyright} 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.; Intelligent Systems Conference, IntelliSys 2023 ; Conference date: 07-09-2023 Through 08-09-2023",
year = "2024",
doi = "10.1007/978-3-031-47715-7_9",
language = "English (US)",
isbn = "9783031477140",
series = "Lecture Notes in Networks and Systems",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "111--127",
editor = "Kohei Arai",
booktitle = "Intelligent Systems and Applications - Proceedings of the 2023 Intelligent Systems Conference IntelliSys Volume 3",
address = "Germany",
}