Distance Regularized Level Set Evolution and Its Application to Image Segmentation
By Chunming Li, Changfeng Gui, Martin D. Fox. 2010
2,154 citations recorded by the source corpus.
Level set methods have been widely used in image processing and computer vision. In conventional level set formulations, the level set function typically develops irregularities during its evolution, which may cause numerical errors and eventually destroy the stability of the evolution. Therefore, a numerical remedy, called reinitialization, is typically applied to periodically replace the degraded level set function with a signed distance function. However, the practice of reinitialization not only raises serious problems as when and how it should be performed, but also affects numerical accuracy in an undesirable way. This paper proposes a new variational level set formulation in which the regularity of the level set function is intrinsically maintained during the level set evolution. The level set evolution is derived as the gradient flow that minimizes an energy functional with a distance regularization term and an external energy that drives the motion of the zero level set toward desired locations. The distance regularization term is defined with a potential function such that the derived level set evolution has a unique forward-and-backward (FAB) diffusion effect, which is able to maintain a desired shape of the level set function, particularly a signed distance profile near the zero level set. This yields a new type of level set evolution called distance regularized level set evolution (DRLSE). The distance regularization effect eliminates the need for reinitialization and thereby avoids its induced numerical errors. In contrast to complicated implementations of conventional level set formulations, a simpler and more efficient finite difference scheme can be used to implement the DRLSE formulation. DRLSE also allows the use of more general and efficient initialization of the level set function. In its numerical implementation, relatively large time steps can be used in the finite difference scheme to reduce the number of iterations, while ensuring sufficient numerical accuracy. To demonstrate the effectiveness of the DRLSE formulation, we apply it to an edge-based active contour model for image segmentation, and provide a simple narrowband implementation to greatly reduce computational cost.
Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Ocean Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Mechanics
- David Dapeng Zhang
- Amlan Kar
- David Acuna
- Lei Zhang
- Huan Ling
- Sanja Fidler
- Gioacchino Viggiani
- Lin F. Yang
In Computer Vision and Pattern Recognition
- Lei Zhang
- Luc Van Gool
- Dacheng Tao
- Ming-Hsuan Yang
- Sanja Fidler
- Xiaogang Wang
- Trevor Darrell
- Jitendra Malik
In Ocean Engineering
- Amlan Kar
- David Acuna
- Sanja Fidler
- Lin F. Yang
- Fuyong Xing
- Anders P. Eriksson
- Dominic Jack
- Mahsa Baktash
Citations in the corpus
- Deep Level Sets: Implicit Surface Representations for 3D Shape Inference (2019, methodology): “Instead we propose the use of an energy functional, similar to the work of [20], that promotes the unit gradient property,”
- Robust Nucleus/Cell Detection and Segmentation in Digital Pathology and Microscopy Images: A Comprehensive Review (2016, methodology): “shape model is incorporated into the level set framework [236] to segment overlapping nuclei and lymphocytes in prostate and breast cancer histopathological images; in [74], the shape prior constraint [235] is integrated in the distance regularized level set model [237], and thus, the method can eff”
- Remote Heart Rate Measurement from Face Videos under Realistic Situations (2014, methodology): “We segment the background region using the Distance Regularized Level Set Evolution (DRLSE) method [11], and use its average green value as a reference to model the illumination variations at the ROI.”
- A Level Set Method for Image Segmentation in the Presence of Intensity Inhomogeneities With Application to MRI (2011, methodology): “Therefore, the regularization term is called a distance regularization term, which was introduced by Li et al. [11] in a more general variational level set formulation called distance regularized level set evolution (DRLSE) formulation.”
- All you need is shape: Predicting shear banding in sand with LS-DEM (2018, methodology): “The segmentation, as well as the gradient of the greyscale image, filtered using a non-local means filter, are used as inputs to level set-imaging algorithms [13, 19, 35],”
- Detection and classification of rice plant diseases (2017, positive): “The shape of the diseased part was extracted using DRLSE method [8].”
- Implicit Surface Representations As Layers in Neural Networks (2019, methodology): “Instead we propose the use of an energy functional, similar to the work of [20], that promotes the unit gradient property, Esdf (φ) = ∫”
- Computer-Aided Diagnosis with Deep Learning Architecture: Applications to Breast Lesions in US Images and Pulmonary Nodules in CT Scans (2016, methodology): “The MORPH features are computed from either experts’ drawings or the computer-generated boundaries by level set 43 (DRLSE) and grow-cut 44 (GC) methods.”
- Devil Is in the Edges: Learning Semantic Boundaries From Noisy Annotations (2019, methodology): “Level Set Methods [27] have been widely used for image segmentation [8, 13, 30, 18, 24, 5, 22, 14] due to their ability to automatically handle various topological changes such as splitting and merging.”
- Object Instance Annotation With Deep Extreme Level Set Evolution (2019, methodology): “In this paper, we follow the remedy proposed in [25], and introduce the distance regularization term to restrict the behavior of LSF.”
- A Level Set Approach to Image Segmentation With Intensity Inhomogeneity (2016, positive): “[28] proposed a signed distance regularization formula.”