Active contour segmentation using level set function with enhanced image from prior intensity

2015 ◽  
Author(s):  
Sunhee Kim ◽  
Youngjun Kim ◽  
Deukhee Lee ◽  
Sehyung Park
Keyword(s):  
Level Set ◽  
Active Contour ◽  
Contour Segmentation ◽  
Level Set Function ◽  
Set Function

scholarly journals Robust Active Contour Model Guided by Local Binary Pattern Stopping Function

2017 ◽  
Vol 17 (4) ◽  
pp. 165-182 ◽  
Author(s):  
Abdallah Azizi ◽  
Kaouther Elkourd ◽  
Zineb Azizi
Keyword(s):  
Level Set ◽  
Active Contour ◽  
Local Binary Pattern ◽  
Active Contour Model ◽  
Intensity Variation ◽  
Level Set Function ◽  
Contour Model ◽  
Local Intensity ◽  
Edge Based ◽  
Set Function

AbstractEdge based active contour models are adequate to some extent in segmenting images with intensity inhomogeneity but often fail when applied to images with poorly defined or noisy boundaries. Instead of the classical and widely used gradient or edge stopping function which fails to stop contour evolution at such boundaries, we use local binary pattern stopping function to construct a robust and effective active contour model for image segmentation. In fact, comparing to edge stopping function, local binary pattern stopping function accurately distinguishes object’s boundaries and determines the local intensity variation dint to the local binary pattern textons used to classify the image regions. Moreover, the local binary pattern stopping function is applied using a variational level set formulation that forces the level set function to be close to a signed distance function to eliminate costly re-initialization and speed up the motion of the curve. Experiments on several gray level images confirm the advantages and the effectiveness the proposed model.

A New Variational Model with Dual Level Set Functions for Selective Segmentation

2012 ◽  
Vol 12 (1) ◽  
pp. 261-283 ◽  
Author(s):  
Lavdie Rada ◽  
Ke Chen
Keyword(s):  
Edge Detection ◽  
Level Set ◽  
Distance Function ◽  
Variational Formulation ◽  
Active Contour ◽  
Geometric Constraints ◽  
Experimental Results ◽  
Variational Model ◽  
Level Set Function ◽  
Set Function

AbstractIn this paper we present a selective segmentation model using a dual level set variational formulation. Our variational model aims to segment all objects with one level set function (global) and the selected object, which is the closest to the geometric constraints (markers), with another level set (local). It is a combination of edge detection, markers distance function and active contour without edges. Experimental results show that our model is more robust than previous work.

scholarly journals Image Segmentation Using Signed Pressure Force Based Active Contour Model

2013 ◽  
Vol 12 (1) ◽  
pp. 3195-3200
Author(s):  
Sagar Chouksey ◽  
Mayur Ghadle ◽  
Shreya Sharma ◽  
Rohan Puranik
Keyword(s):  
Level Set ◽  
Active Contour ◽  
Active Contour Model ◽  
Computational Cost ◽  
Initial Contour ◽  
Pressure Force ◽  
Binary Function ◽  
Level Set Function ◽  
Contour Model ◽  
Set Function

A novel signed pressure force (SPF) based active contour model (ACM) is proposed in this work. It is implemented with help of Gaussian filtering regularized level set method, which first selectively penalizes the level set function to be binary, and then uses a Gaussian smoothing kernel to regularize it. The advantages of this method are as follows. First, a new region-based signed pressure force (SPF) function is proposed, which can efficiently stop the contours at weak or blurred edges. Second, the exterior and interior boundaries can be automatically detected with the initial contour being anywhere in the image. Third, the proposed SPF with ACM has the property of selective local or global segmentation. It can segment not only the desired object but also the other objects. Fourth, the level set function can be easily initialized with a binary function, which is more efficient. The computational cost for traditional re-initialization can also be reduced.

An Improved Integrated Active Contour Model without Re-Initialization for Vector-Valued Images Segmentation

2012 ◽  
Vol 429 ◽  
pp. 271-276 ◽  
Author(s):  
Ji Zhao ◽  
Fu Qun Shao ◽  
Ji Zhao ◽  
Xue Dong Zhang ◽  
Chuang Feng
Keyword(s):  
Level Set ◽  
Active Contour ◽  
Active Contours ◽  
Active Contour Model ◽  
Nonlinear Heat Equation ◽  
Level Set Function ◽  
Implementation Scheme ◽  
Level Set Evolution ◽  
Set Function ◽  
Vector Images

In this paper, an improved variational formulation for active contours model is introduced to force level set function to become fast and stably close to signed distance function, which can completely eliminate the need of the costly re-initialization procedure. A restriction item that is a nonlinear heat equation with balanced diffusion rate is attached to variational Integrated Active Contour (IAC) model on the basis of analysis on regions and edges information from all channels of the valued-vector images, so that the level set evolution segmentation process becomes fast and stable. In addition, more efficient discretization method with spatial rotation-invariance gradient and divergence operator is proposed as numerical implementation scheme. Finally, the experiments on some images have demonstrated the efficiency, accuracy and robustness of the proposed method.

Image Segmentation Using Binary Level Set Method Based on Region-Based GAC Model

2011 ◽  
Vol 480-481 ◽  
pp. 1206-1209 ◽  
Author(s):  
Ge Ren ◽  
Xing Qin Cao ◽  
Wei Min Pan ◽  
Yong Yang
Keyword(s):  
Level Set Method ◽  
Level Set ◽  
Active Contour ◽  
Active Contour Model ◽  
Computational Cost ◽  
Geodesic Active Contour ◽  
Level Set Function ◽  
Contour Model ◽  
Set Function ◽  
Better Than

A new Region-based GAC (geodesic active contour) model was presented, which is the improvement of traditional GAC model. A new region-based signed pressure forces function was presented, which takes the place of the edge stopping function, and can efficiently solve the problem of segmentation of objects with weak edges or without edges. The model is implemented by level set method with a binary level set function to reduce the expensive computational cost of re-initialization of the traditional level set function. The proposed algorithm has been applied to images of different modalities with promising results, which are better than that of traditional GAC model and C-V model.

Active Contour Driven by Edge and Region Image Fitting Energy

2012 ◽  
Vol 532-533 ◽  
pp. 892-896
Author(s):  
Hai Yong Xu ◽  
Ming Hua Liu
Keyword(s):  
Level Set ◽  
Active Contour ◽  
Active Contour Model ◽  
Energy Functional ◽  
Global Information ◽  
Geodesic Curve ◽  
Regularization Term ◽  
Level Set Function ◽  
Contour Model ◽  
Set Function

In this paper, we propose a novel edge and region-based active contour model. We consider geodesic curve and region-based model, and evolve a contour based on global information. Moreover, we add to the level set regularization term in the energy functional to ensure accurate computation and avoids expensive re-initialization of the level set function. Experiments on synthetic and real images show desirable performances of our method.

scholarly journals An Image Segmentation Method Based on Improved Regularized Level Set Model

2018 ◽  
Vol 8 (12) ◽  
pp. 2393 ◽  
Author(s):  
Lin Sun ◽  
Xinchao Meng ◽  
Jiucheng Xu ◽  
Shiguang Zhang
Keyword(s):  
Image Segmentation ◽  
Level Set ◽  
Energy Functional ◽  
External Energy ◽  
Regularization Term ◽  
Level Set Function ◽  
New Energy ◽  
Segmentation Approach ◽  
Set Function ◽  
Distance Regularization

When the level set algorithm is used to segment an image, the level set function must be initialized periodically to ensure that it remains a signed distance function (SDF). To avoid this defect, an improved regularized level set method-based image segmentation approach is presented. First, a new potential function is defined and introduced to reconstruct a new distance regularization term to solve this issue of periodically initializing the level set function. Second, by combining the distance regularization term with the internal and external energy terms, a new energy functional is developed. Then, the process of the new energy functional evolution is derived by using the calculus of variations and the steepest descent approach, and a partial differential equation is designed. Finally, an improved regularized level set-based image segmentation (IRLS-IS) method is proposed. Numerical experimental results demonstrate that the IRLS-IS method is not only effective and robust to segment noise and intensity-inhomogeneous images but can also analyze complex medical images well.

A Method for Tracking a Solid Body in a Fluid Field in Immersed Boundary Methods

2018 ◽  
Author(s):  
Guangfa Yao
Keyword(s):  
Level Set ◽  
Solid Body ◽  
Volume Fraction ◽  
Transformation Matrix ◽  
The Body ◽  
New Method ◽  
Immersed Boundary ◽  
Body Interaction ◽  
Level Set Function ◽  
Set Function

Immersed boundary method has got increasing attention in modeling fluid-solid body interaction using computational fluid dynamics due to its robustness and simplicity. It usually simulates fluid-solid body interaction by adding a body force in the momentum equation. This eliminates the body conforming mesh generation that frequently requires a very labor-intensive and challenging task. But accurately tracking an arbitrary solid body is required to simulate most real world problems. In this paper, a few methods that are used to track a rigid solid body in a fluid domain are briefly reviewed. A new method is presented to track an arbitrary rigid solid body by solving a transformation matrix and identifying it using a level set function. Knowing level set function, the solid volume fraction can be derived if needed. A three-dimensional example is used to study a few methods used to represent and solve the transformation matrix, and demonstrate the presented new method.

Sign in / Sign up

Export Citation Format

Share Document