Geodesic active regions for supervised texture segmentation

Paragios, Nikolaos; Deriche, Rachid

doi:10.1109/iccv.1999.790347

Cited by 441 publications

(575 citation statements)

References 21 publications

Supporting

Mentioning

563

Contrasting

Unclassified

Order By: Relevance

“…Although initially introduced for supervised texture segmentation, the geodesic active region model has been extended to address unsupervised image segmentation [13], [14]. It has also been successfully exploited to provide an elegant solution to motion estimation and the tracking problem.…”

Section: Geodesic Active Region Modelmentioning

confidence: 99%

“…To overcome the leakage problem, ChanVese suggested the use of the region information of the target object for segmentation [12], [13]. They proposed to minimize the following energy function with respect to c 1 , c 2 , and C:…”

Section: Chan-vese Minimal Variance Modelmentioning

confidence: 99%

“…Image segmentation is one of the most important steps in the analysis of preprocessed patient image data and can be helpful in diagnosis, treatment planning, and treatment delivery, among other applications [1]- [3]. It is the process of labeling each pixel in a medical image dataset to indicate its tissue type or anatomical structure.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Medical Image Segmentation Using Level Set Method with a New Hybrid Speed Function Based on Boundary and Region Segmentation

Park

Cho

2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis paper presents a new hybrid speed function needed to perform image segmentation within the level-set framework. The proposed speed function uses both the boundary and region information of objects to achieve robust and accurate segmentation results. This speed function provides a general form that incorporates the robust alignment term as a part of the driving force for the proper edge direction of an active contour, an active region term derived from the region partition scheme, and the smoothing term for regularization. First, we use an external force for active contours as the Gradient Vector Flow field. This is computed as the diffusion of gradient vectors of a gray level edge map derived from an image. Second, we partition the image domain by progressively fitting statistical models to the intensity of each region. Here we adopt two Gaussian distributions to model the intensity distribution of the inside and outside of the evolving curve partitioning the image domain. Third, we use the active contour model that has the computation of geodesics or minimal distance curves, which allows stable boundary detection when the model's gradients suffer from large variations including gaps or noise. Finally, we test the accuracy and robustness of the proposed method for various medical images. Experimental results show that our method can properly segment low contrast, complex images. key words: image segmentation, geometric deformable model, level set method, gradient vector flow

show abstract

Section: Geodesic Active Region Modelmentioning

confidence: 99%

Section: Chan-vese Minimal Variance Modelmentioning

confidence: 99%

See 1 more Smart Citation

Medical Image Segmentation Using Level Set Method with a New Hybrid Speed Function Based on Boundary and Region Segmentation

Park

Cho

2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…Using of variational methods in image segmentation has been popular in past decades [5][6][7][8]. Because variational models can combine image information and prior information in a unified framework, the segmentation results are more robust compared to some classical methods.…”

Section: Introductionmentioning

confidence: 99%

Variational Sar Image Segmentation Based on the G0 Model and an Augmented Lagrangian Method

Feng¹,

Cao

Pi³

2012

PIER B

View full text Add to dashboard Cite

Abstract-This paper present a fast algorithm for synthetic aperture radar (SAR) image segmentation based on the augmented Lagrangian method (ALM). The proposed approach considers the segmentation of SAR images as an energy minimization problem in a variational framework. The energy functional is formulated based on the statistical characteristic of SAR images. The total variation regularization is used to impose the smoothness constraint of the segmentation result. To solve the optimization problem efficiently, the energy functional is firstly modified to be convex and differentiable by using convex relaxing and variable splitting techniques, and then the constrained optimization problem is converted to an unconstrained one by using the ALM. Finally the energy is minimized with an iterative minimization algorithm. The effectiveness of the proposed algorithm is validated by experiments on both synthetic and real SAR images.

show abstract

“…The basic idea of active contour model is to evolve a curve under some constraints to extract the desired object. According to the nature of constraints, the existing active contour models can be categorized into two types: edge-based models [4]- [5] and region-based models [6], [7]- [10].…”

Section: Introductionmentioning

confidence: 99%

Global Region Based Segmentation of Satellite and Medical Imagery with Active Contours and Level Set Evolution on Noisy Images

Ramudu¹,

Reddy²,

Srinivas³

et al. 2013

IJAPM

View full text Add to dashboard Cite

Abstract-In this paper, we proposed a novel global segmentation method for satellite images with active contour model on noisy images with ten percentage of salt and pepper. It was implemented with a special technique selective binary and Gaussian filtering regularized level set evolution. First we selectively penalize the level set function to be binary and then use a Gaussian smoothing kernel to regularize it. The advantages of our method is a new region based signed pressure force(SPF) function is proposed, which can step effectively the contour at weak or blurred edges and automatically detect the interior and exterior boundaries with the initial contour being anywhere in the images effected with noise. The proposed method can implement by the simple finite difference scheme. Experiments on satellite images with noise demonstrate the advantages of the proposed method over the Chan-vase (CV) active contour in terms of the number of Iterations.Index Terms-Active contours, image segmentation, Chan-vase model, level set method.

show abstract

Geodesic active regions for supervised texture segmentation

Cited by 441 publications

References 21 publications

Medical Image Segmentation Using Level Set Method with a New Hybrid Speed Function Based on Boundary and Region Segmentation

Medical Image Segmentation Using Level Set Method with a New Hybrid Speed Function Based on Boundary and Region Segmentation

Variational Sar Image Segmentation Based on the G0 Model and an Augmented Lagrangian Method

Global Region Based Segmentation of Satellite and Medical Imagery with Active Contours and Level Set Evolution on Noisy Images

Contact Info

Product

Resources

About