scholarly journals Comparative analysis and implementation of structured Edge Active Contour

2020 ◽  
Vol 10 (2) ◽  
pp. 1842
Author(s):  
Brijesh N. Shah ◽  
Jaymin K. Bhalani
Keyword(s):  
Active Contour ◽  
Active Contour Model ◽  
Linear Structure ◽  
Structure Tensor ◽  
Novel Structure ◽  
Intensity Information ◽  
Proposed Model ◽  
Blurred Image ◽  
Derivative Information ◽  
Computing Structure

This paper proposes modified chanvese model which can be implemented on image for segmentation. The structure of paper is based on Linear structure tensor (LST) as input to the variant model. Structure tensor is a matrix illustration of partial derivative information. In the proposed model, the original image is considered as information channel for computing structure tensor. Difference of Gaussian (DOG) is featuring improvement in which we can get less blurred image than original image.In this paper LST is modified by adding intensity information to enhance orientation information. Finally Active Contour Model (ACM) is used to segment the images. The proposed algorithm is tested on various images and also on some images which have intensity inhomogeneity and results are shown. Also, the results with other algorithms like chanvese, Bhattacharya, Gabor based chanvese and Novel structure tensor based model are compared.It is verified that accuracy of proposed model is the best. The biggest advantage of proposed model is clear edge enhancement.

scholarly journals A Fast Region-Based Segmentation Model with Gaussian Kernel of Fractional Order

2013 ◽  
Vol 2013 ◽  
pp. 1-7 ◽  
Author(s):  
Bo Chen ◽  
Qing-Hua Zou ◽  
Wen-Sheng Chen ◽  
Yan Li
Keyword(s):  
Fractional Order ◽  
Energy Function ◽  
Active Contour ◽  
Active Contour Model ◽  
Gaussian Kernel ◽  
Proposed Model ◽  
Function Expression ◽  
Local Mean ◽  
Geometric Active Contour ◽  
Evolution Curve

By summarizing some classical active contour models from the view of level set representation, a simple energy function expression with the Gaussian kernel of fractional order is proposed, and then a novel region-based geometric active contour model is established. In this proposed model, the energy function with value of [−1, 1] is built, the local mean and global mean of the inside and outside of the evolution curve are employed, and the segmentation results are obtained by controlling the expansion and contraction of the evolution curve. The model is simple and easy to implement; it can also protect weak edges because of considering more statistical information. Experimental results on synthetic and natural images show that the proposed model is much more effective in dealing with the images with weak or blurred edges, and it takes less time.

Active Contour Model Coupling Local and Global Information

2015 ◽  
Vol 719-720 ◽  
pp. 1155-1159 ◽  
Author(s):  
Zhi Feng Wang
Keyword(s):  
Model Experiment ◽  
Active Contour ◽  
Active Contour Model ◽  
Data Fitting ◽  
Local Region ◽  
Model Coupling ◽  
Global Information ◽  
Contour Model ◽  
Intensity Information ◽  
Cv Model

The local region term and global region term are combined for image segmentation. Intensity information in local regions is utilized by adding a kernel function in the data fitting term. Experiments have been done on different images to compare the effectiveness of our methods with that of the classic CV model, Li’s Local Binary Fitting (LBF) model. Experiment results show that the new model maintain more satisfactory segmentation results.

A Local Statistical Information Active Contour Model for Image Segmentation

2014 ◽  
Vol 6 (2) ◽  
pp. 33-49 ◽  
Author(s):  
Shigang Liu ◽  
Yali Peng ◽  
Guoyong Qiu ◽  
Xuanwen Hao
Keyword(s):  
Active Contour ◽  
Active Contour Model ◽  
Energy Functional ◽  
Statistical Information ◽  
Intensity Inhomogeneity ◽  
Image Domain ◽  
Contour Model ◽  
Proposed Model ◽  
Spatially Varying ◽  
Level Set Formulation

This paper presents a local statistical information (LSI) active contour model. Assuming that the distribution of intensity belonging to each region is a Gaussian distribution with spatially varying statistical information, and defining an energy function, the authors integrate the entire image domain. Then, this energy is incorporated into a variational level set formulation. Finally, by minimizing the energy functional, a curve evolution equation can be obtained. Because the image local information is considered, the proposed model can effectively deal with the image with intensity inhomogeneity. Experimental results on synthetic and real images demonstrate that the proposed model can effectively segment the image with intensity inhomogeneity.

scholarly journals Implicit Active Contour Model with Local and Global Intensity Fitting Energies

2013 ◽  
Vol 2013 ◽  
pp. 1-13 ◽  
Author(s):  
Xiaozeng Xu ◽  
Chuanjiang He
Keyword(s):  
Steady State ◽  
Initial Function ◽  
Active Contour ◽  
Active Contour Model ◽  
Level Line ◽  
Zero Level ◽  
Contour Model ◽  
Proposed Model ◽  
Local Intensity ◽  
Global Image Information

We propose a new active contour model which integrates a local intensity fitting (LIF) energy with an auxiliary global intensity fitting (GIF) energy. The LIF energy is responsible for attracting the contour toward object boundaries and is dominant near object boundaries, while the GIF energy incorporates global image information to improve the robustness to initialization of the contours. The proposed model not only can provide desirable segmentation results in the presence of intensity inhomogeneity but also allows for more flexible initialization of the contour compared to the RSF and LIF models, and we give a theoretical proof to compute a unique steady state regardless of the initialization; that is, the convergence of the zero-level line is irrespective of the initial function. This means that we can obtain the same zero-level line in the steady state, if we choose the initial function as a bounded function. In particular, our proposed model has the capability of detecting multiple objects or objects with interior holes or blurred edges.

scholarly journals Fractional Differentiation-Based Active Contour Model Driven by Local Intensity Fitting Energy

2016 ◽  
Vol 2016 ◽  
pp. 1-10 ◽  
Author(s):  
Ming Gu ◽  
Renfang Wang
Keyword(s):  
Fractional Order ◽  
Level Set ◽  
Active Contour ◽  
Active Contour Model ◽  
Input Image ◽  
Intensity Inhomogeneity ◽  
Initial Contour ◽  
Level Set Function ◽  
Contour Model ◽  
Proposed Model

A novel active contour model is proposed for segmentation images with inhomogeneity. Firstly, fractional order filter is defined by eight convolution masks corresponding to the image orientation in the eight compass directions. Then, the fractional order differentiation image is obtained and applied to the level set method. Secondly, we defined a new energy functional based on local image information and fractional order differentiation image; the proposed model not only can describe the input image more accurately but also can deal with intensity inhomogeneity. Local fitting term can enhance the ability of the model to deal with intensity inhomogeneity. The defined penalty term is used to reduce the occurrence of false boundaries. Finally, in order to eliminate the time-consuming step of reinitialization and ensure stable evolution of level set function, the Gaussian filtering method is used. Experiments on synthetic and real images show that the proposed model is efficient for images with intensity inhomogeneity and flexible to initial contour.

scholarly journals A Vessel Active Contour Model for Vascular Segmentation

2014 ◽  
Vol 2014 ◽  
pp. 1-15 ◽  
Author(s):  
Yun Tian ◽  
Qingli Chen ◽  
Wei Wang ◽  
Yu Peng ◽  
Qingjun Wang ◽  
...  
Keyword(s):  
Vector Field ◽  
Active Contour ◽  
Active Contour Model ◽  
Contour Model ◽  
Proposed Model ◽  
Weighted Means ◽  
Speed Up ◽  
Local Intensity ◽  
Local Binary Fitting Model ◽  
Vessel Tree

This paper proposes a vessel active contour model based on local intensity weighting and a vessel vector field. Firstly, the energy function we define is evaluated along the evolving curve instead of all image points, and the function value at each point on the curve is based on the interior and exterior weighted means in a local neighborhood of the point, which is good for dealing with the intensity inhomogeneity. Secondly, a vascular vector field derived from a vesselness measure is employed to guide the contour to evolve along the vessel central skeleton into thin and weak vessels. Thirdly, an automatic initialization method that makes the model converge rapidly is developed, and it avoids repeated trails in conventional local region active contour models. Finally, a speed-up strategy is implemented by labeling the steadily evolved points, and it avoids the repeated computation of these points in the subsequent iterations. Experiments using synthetic and real vessel images validate the proposed model. Comparisons with the localized active contour model, local binary fitting model, and vascular active contour model show that the proposed model is more accurate, efficient, and suitable for extraction of the vessel tree from different medical images.

Sign in / Sign up

Export Citation Format

Share Document