Fast global region based minimization of satellite and medical imagery with geometric active contour and level set evolution on noisy images

An Adaptive image segmentation algorithm based on geometric active contour (GAC) model was presented in this paper in order to solve the problem that tradition GAC model can not segment adaptively. By combining the regional information to construct energy functional description area information. We propose an improved adaptive image segmentation algorithm, This algorithm combines the advantages of GAC model and C-V model effectively, Regional energy functional could determine the evolution speed to replace the constant evolution speed in traditional GAC model. Experimental results showed that the proposed algorithm is feasible, and reaches an obvious effect in terms of boundary leaking.

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.

Image segmentation is a classical and crucial problem in the fields of computer vision and image understanding. Since Kass et al. proposed the seminal model, i.e. snake, active contour model has rapid development and becomes a research hotspot. It mainly includes parametric active contour model and geometric active contour model. Geometric active contour model has many advantages over parametric active contour model, such as computational simplicity and the ability to change curve topology during deformation. Therefore, this paper gives a review on geometric active contour model, the three types of active contour models, i.e. edge-based, region-based and edge-region based models are presented, their advantages and drawbacks are summarized, a number of improvements are analyzed in detail. Finally, the paper makes prospect for the future of active contour model.

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 any where 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.

Breast cancer is one of the major causes of death among women all over the world. The most frequently used diagnosis tool to detect breast cancer is ultrasound. However, to segment the breast ultrasound images is a difficult thing. Some studies show that the active contour models have been proved to be the most successful methods for medical image segmentation. The level set method is a class of curve evolution methods based on the geometric active contour model. Morphological operation describes a range of image processing technique that deal with the shape of features in an image. Morphological operations are applied to remove imperfections that introduced during segmentation. In this paper, we have evaluated three level set methods that combined with morphological operations to segment the breast lesions. The level set methods that used in our research are the Chan Vese (C-V) model, the Selective Binary and Gaussian Filtering Regularized Level Set (SBGFRLS) model and the Distance Regularized Level Set Evolution (DRLSE) model. Furthermore, to evaluate the method, we compared the segmented breast lesion that obtained by each method with the lesion that obtained manually by radiologists. The evaluation is done by four metrics: Dice Similarity Coefficient (DSC), True-Positive Ratio (TPR), True-Negative Ratio (TNR), and Accuracy (ACC). Our experimental results with 30 breast ultrasound images showed that the C-V model that combined with morphological operations have better performance than the other two methods according to mean value of DSC metrics.

The technique of geometric active contours has become quite popular for a variety of applications, particularly image segmentation and classification problems. In traditional active contour models, snake initialization is performed manually by users, and topological changes, such as splitting of the snake, can not be automatically handled. In this paper, we present an automatic geometric active contours model which can extract multiple objects in an image without any manual assistance and completely eliminates the need of costly re-initialization procedure. The proposed framework is inspired by the geodesic active contour model and leads to a paradigm that is relatively free from the initial curve position. According to the proposed flow, the traditional boundary attraction term is replaced with a new force that guides the propagation to the object boundaries from both sides. This new geometric active contour model is implemented using a level set approach, thereby allowing dealing naturally with topological changes.KeywordsLevel setsGeodesic active contourMultiple objects segmentation

A novel generalized gradient vector flow snake model using minimal surface and component-normalized method for medical image segmentation

Active contour methods (ACM) are model-based approaches for image segmentation and were developed in the late 1980s. ACM can be divided into two classes: parametric active contour model and geometric active contour model. Geometric method is intrinsic model. Because of its completeness in mathematics, geometric active contour model overcomes many difficulties of the parametric active contour model. However, in medical images with heavy structural noise, the evolution of the geometric active contour will be seriously affected. To handle this problem, this paper proposed a multiscale geometric active contour model, based on the multiscale analysis method—bidimensional empirical mode decomposition. In the human kidney MR images, the proposed multiscale geometric active contour model successfully extracts the complex kidney contour.

Learned snakes for 3D image segmentation

Lennard-Jones force field for geometric active contour

Segmentation is an important step in medical image analysis. This process is crucial but challenging due to inhomogeneneity in intensity of images. In addition, the images are often corrupted by noise and with contrast edges. There are some approaches aiming to cope with this kind of images such as: region growing, region competition, watershed segmentation, global thresholding, and active contour methods. Among them, active contour methods, especially level set-based active contour is widely used for image segmentation by their advantageous properties such as topology adaptability, and robustness to initialization. In this paper, we present and demonstrate the effectiveness of some recently active contour models for segmenting medical images with inhomogeneity in intensity. Among these techniques, the local binary fitting based model is validated as a promising method for medical image segmentation.

An important branch of computer vision is image segmentation. Image segmentation aims at extracting meaningful objects lying in images either by dividing images into contiguous semantic regions, or by extracting one or more specific objects in images such as medical structures. The image segmentation task is in general very difficult to achieve since natural images are diverse, complex and the way we perceive them vary according to individuals. For more than a decade, a promising mathematical framework, based on variational models and partial differential equations, have been investigated to solve the image segmentation problem. This new approach benefits from well-established mathematical theories that allow people to analyze, understand and extend segmentation methods. Moreover, this framework is defined in a continuous setting which makes the proposed models independent with respect to the grid of digital images. This thesis proposes four new image segmentation models based on variational models and the active contours method. The active contours or snakes model is more and more used in image segmentation because it relies on solid mathematical properties and its numerical implementation uses the efficient level set method to track evolving contours. The first model defined in this dissertation proposes to determine global minimizers of the active contour/snake model. Despite of great theoretic properties, the active contours model suffers from the existence of local minima which makes the initial guess critical to get satisfactory results. We propose to couple the geodesic/geometric active contours model with the total variation functional and the Mumford-Shah functional to determine global minimizers of the snake model. It is interesting to notice that the merging of two well-known and opposite models of geodesic/geometric active contours, based on the detection of edges, and active contours without edges provides a global minimum to the image segmentation algorithm. The second model introduces a method that combines at the same time deterministic and statistical concepts. We define a non-parametric and non-supervised image classification model based on information theory and the shape gradient method. We show that this new segmentation model generalizes, in a conceptual way, many existing models based on active contours, statistical and information theoretic concepts such as mutual information. The third model defined in this thesis is a variational model that extracts in images objects of interest which geometric shape is given by the principal components analysis. The main interest of the proposed model is to combine the three families of active contours, based on the detection of edges, the segmentation of homogeneous regions and the integration of geometric shape prior, in order to use simultaneously the advantages of each family. Finally, the last model presents a generalization of the active contours model in scale spaces in order to extract structures at different scales of observation. The mathematical framework which allows us to define an evolution equation for active contours in scale spaces comes from string theory. This theory introduces a mathematical setting to process a manifold such as an active contour embedded in higher dimensional Riemannian spaces such as scale spaces. We thus define the energy functional and the evolution equation of the multiscale active contours model which can evolve in the most well-known scale spaces such as the linear or the curvature scale space.

Accurate segmentation of magnetic resonance (MR) images of the brain to differentiate features such as soft tissue, tumor, edema and necrosis is critical for both diagnosis and treatment purposes. Region-based formulations of geometric active contour models are popular choices for segmentation of MR and other medical images. Most of the traditional region-based formulations model local region intensity by assuming a piecewise constant approximation. However, the piecewise constant approximation rarely holds true for medical images such as MR images due to the presence of noise and bias field, which invariably results in a poor segmentation of the image. To overcome this problem, we have developed a probabilistic region-based active contour model for automatic segmentation of MR images of the brain. In our approach, a mixture of Gaussian distributions is used to accurately model the arbitrarily shaped local region intensity distribution. Prior spatial information derived from probabilistic atlases is also integrated into the level set evolution framework for guiding the segmentation process. Our experiments with a series of publicly available brain MR images show that the proposed active contour model gives stable and accurate segmentation results when compared to the traditional region based formulations.

Active contour models based on the level set method (LSM) are widely used in image segmentation. The major advantages of these models based on an LSM are topological flexibility and evolution robustness. However, topological flexibility is not always needed, and it could bring some negative effects for object extraction, such as extracting noise and non-objects. In this paper, a topological preservation method is proposed to constrain the evolution of contour. First, the modes of topological changes in geometric active contour models are analyzed. Second, on the basis of the modes of topological changes, the corresponding constraints are designed to keep the topology. To be specific, extracting objects with a known topology (such as k-connected objects) is viewed as a sparse representation problem under a set of basis functions. According to sparse representation, the increase or decrease of evolving contours’ topology corresponds to those of the basis functions. Thus, a corresponding energy functional for topology preservation is defined based on basis functions. Finally, the proposed constraint is integrated into geometric active contour models, which is useful in extracting special objects. Experiments demonstrate that the proposed method improves the robustness of the performance of active contour models and can increase the accuracy in target object extraction.

Geometric active contour model has many advantages over parametric active contour model, such as computational simplicity and the ability to change curve topology during deformation, et al. The level set method is a class of curve evolution methods based on the geometry active contour model. Level set method coupled with curve evolution theory conquers many limitations of traditional snakes, which widens the utilization of active contours model. Moreover, by analyzing latest level set method, this paper summarizes the research, development and applications of active contour model. Finally, this paper points out future research orientations on the theories and applications research of level set method. Index Terms - Image segmentation, level set, active contour mode.