Abstract:Abstract. In this paper, we propose a new model for active contours to detect objects in a given image, based on techniques of curve evolution, Mumford-Shah functional for segmentation and level sets. Our model can detect objects whose boundaries are not necessarily defined by gradient. The model is a combination between more classical active contour models using mean curvature motion techniques, and the Mumford-Shah model for segmentation. We minimize an energy which can be seen as a particular case of the so… Show more
“…The Chan-Vese active contour [30] is a region-based level-set model which is particularly suited to 2D-GE image segmentation due to its robustness to the presence of noise, its topological adaptability, as well as its capability of detecting smooth boundaries or boundaries that are not defined by gradient, as is the case with protein spots. The mathematical formulation of the Chan-Vese active contour adopts the reduced case of the Mumford-Shah problem [31], resulting in the following evolution equation: …”
Section: The Chan-vese Active Contour On 2d-ge Imagesmentioning
This work introduces a novel active contour-based scheme for unsupervised segmentation of protein spots in two-dimensional gel electrophoresis (2D-GE) images. The proposed segmentation scheme is the first to exploit the attractive properties of the active contour formulation in order to cope with crucial issues in 2D-GE image analysis, including the presence of noise, streaks, multiplets and faint spots. In addition, it is unsupervised, providing an alternate to the laborious, error-prone process of manual editing, which is required in state-of-the-art 2D-GE image analysis software packages. It is based on the formation of a spottargeted level-set surface, as well as of morphologically-derived active contour energy terms, used to guide active contour initialization and evolution, respectively. The experimental results on real and synthetic 2D-GE images demonstrate that the proposed scheme results in more plausible spot boundaries and outperforms all commercial software packages in terms of segmentation quality.
“…The Chan-Vese active contour [30] is a region-based level-set model which is particularly suited to 2D-GE image segmentation due to its robustness to the presence of noise, its topological adaptability, as well as its capability of detecting smooth boundaries or boundaries that are not defined by gradient, as is the case with protein spots. The mathematical formulation of the Chan-Vese active contour adopts the reduced case of the Mumford-Shah problem [31], resulting in the following evolution equation: …”
Section: The Chan-vese Active Contour On 2d-ge Imagesmentioning
This work introduces a novel active contour-based scheme for unsupervised segmentation of protein spots in two-dimensional gel electrophoresis (2D-GE) images. The proposed segmentation scheme is the first to exploit the attractive properties of the active contour formulation in order to cope with crucial issues in 2D-GE image analysis, including the presence of noise, streaks, multiplets and faint spots. In addition, it is unsupervised, providing an alternate to the laborious, error-prone process of manual editing, which is required in state-of-the-art 2D-GE image analysis software packages. It is based on the formation of a spottargeted level-set surface, as well as of morphologically-derived active contour energy terms, used to guide active contour initialization and evolution, respectively. The experimental results on real and synthetic 2D-GE images demonstrate that the proposed scheme results in more plausible spot boundaries and outperforms all commercial software packages in terms of segmentation quality.
“…To our knowledge, there have been no solutions proposed for carpal tunnel segmentation other than the proposed method. Therefore, two popular deformable model-based methods, the conventional snake [19] and the Chan-Vese method [33], were selected for comparison. For the conventional snake, it is firstly considered that an initial contour is required for snake deformation on each image slice.…”
Section: Comparative Studymentioning
confidence: 99%
“…4). As to the Chan-Vese method, which does not require an explicit initial contour, it can achieve segmentation by evolving an implicit curve (i.e., zero-level) based on the deduction of Euler-Lagrange equation [33]. Overall, the parameters of the Chan-Vese and conventional snake methods were selected empirically to obtain the best results.…”
Carpal tunnel syndrome (CTS) has been reported as one of the most common peripheral neuropathies. Carpal tunnel segmentation from magnetic resonance (MR) images is important for the evaluation of CTS. To date, manual segmentation, which is time-consuming and operator dependent, remains the most common approach for the analysis of the carpal tunnel structure. Therefore, we propose a new knowledge-based method for automatic segmentation of the carpal tunnel from MR images. The proposed method first requires the segmentation of the carpal tunnel from the most proximally cross-sectional image. Three anatomical features of the carpal tunnel are detected by watershed and polygonal curve fitting algorithms to automatically initialize a deformable model as close to the carpal tunnel in the given image as possible. The model subsequently deforms toward the tunnel boundary based on image intensity information, shape bending degree, and the geometry constraints of the carpal tunnel. After the deformation process, the carpal tunnel in the most proximal image is segmented and subsequently applied to a contour propagation step to extract the tunnel contours sequentially from the remaining cross-sectional images. MR volumes from 15 subjects were included in the validation experiments. Compared with the ground truth of two experts, our method showed good agreement on tunnel segmentations by an average margin of error within 1 mm and dice similarity coefficient above 0.9.
“…Those two steps are implemented iteratively until some convergent criterion is satisfied. This kind minimization strategy is a common choice in variational image segmentation algorithms [7,10].…”
Section: The Variational Formulation Of Sar Image Segmentationmentioning
confidence: 99%
“…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.…”
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.