Image segmentation based on geodesic aided Chan-Vese model

The geodesic active contour (GAC) model has been widely used due to the high precision of edge detection and the continuity of boundaries. However, compared to the gradient vector flow (GVF) field, it usually has poor performance in the object boundaries with concave shape. In this paper, the improvements that integrate the good performance of the GAC model and the GVF field are described in detail and the GAC_GVF&B model combining the GAC model with the GVF field and a balloon force is proposed. The experimental results demonstrate that the proposed method is insensitive to the positions of initial curves and can segment complex-shape or multi-objects images correctly with higher convergence.

In this paper, a novel algorithm for intensity inhomogeneous image segmentation is proposed. The presented method introduces a signed pressure force function using the local information of the image to be segmented. Thus, this model can work with heterogeneous images. In addition, by taking the advantages of Geodesic active contour (GAC) and Chan-Vese (C-V) model, the mehod could deal with objects even with discrete /blur boundaries and gives exact results in detecting object boundaries. Experimental results demonstrate that the proposed model is effective in segmenting inhomogeneous images and promising in pattern recognition.

Multiple piecewise constant with geodesic active contours (MPC-GAC) framework for interactive image segmentation using graph cut optimization

Active contours driven by local likelihood image fitting energy for image segmentation

C-V model has the advantage of being able to detect boundaries of objects that are not defined by gradient. However, when detecting these types of edges, the C-V model only considers the average value of each region without local information. As a result, its segmentation result may exist errors, when detecting non-gradient defined boundaries. In order to overcome this problem, we modify the fitting term of classical C-V model with an extra weight. This weight can control the relative height of zero-level contour, so the new method can decrease the segmentation errors. Experiments show that the new model can obtain more accurate results and segment multi-phase images by setting proper weights. Active contour models (1), based on level set method, are one important type of methods in image segmentation. Those methods can handle topological changes automatically, and can get the boundaries of objects with complex edges. At present, there are two categories of active contour methods. One is based on the edge information and the other is based on the region information. Snakes (2), geometric active contours (3), geodesic active contours (GAC) model (4) are edge-based models. These methods get the boundaries of objects from the gradients of images. As these methods depend on the gradient information, when processing images with non-gradient defined edges, they will get wrong boundaries. While M-S model (5) and C-V model (6) are based on global region information. They take piecewise constant patches as the solution of segmentation problems. As a result, it can process the images whose edges are not well defined. Additionally, C-V model can process images fast and segment the objects with inner-boundaries, and its solution is robust to the initialization of the curves. However, C-V model may have problems when detecting blurred and fuzzy edges. The reason is that the C-V model only considers the averages inside and outside the zero-level contours, and the results determined by its energy functional may be not suitable for these edge types. In this paper, we propose an improved C-V model with a generalized fitting term to deal with the above problem. A weight factor w added into the generalized fitting term, controls the height of zero-level sets of the original C-V model. Thus we may obtain accurate segmentation results by

In this paper, we introduce multi-symplectic Lagrangian variational integrators for solving Chan-Vese active contour models in image segmentation. Energy functionals are discretized firstly, and numerical schemes are derived from discrete Euler-Lagrange equations based on discrete variational principle. Lagrangian variational integrators preserve native differential structure-multi-symplecticity, that makes the numerical methods have a satisfied behavior. Experiments are performed on the benchmark images from literature. We further evaluated the methods in a segmentation database containing 1023 images. It shows that the proposed numerical schemes attain relatively faster convergence rates and better segmentation accuracy. Comparisons with the standard explicit Euler method of the original Chan-Vese model and other fast numerical optimization methods show that the proposed methods have better stability, higher accuracy, and are more robust when dealing with a large number of pictures. This study provides an example for further research to improve the performance of other existing image segmentation methods based on active contour models.

The precision of grinding and positioning by industry robot is influenced by segmentation accuracy of region of interest (ROI). The inherent defects of casting billet including perforation defects, crack defects, surface defects, and the polluted environment of post-processing may cause poor imaging quality which may have adverse effects on image segmentation. Considering the need for localization and identification in casting post-processing production line, this paper proposed a novel active contour algorithm which is suitable for the segmentation of complex images. First of all, the penalty term based on the local gradient information of image was introduced into the energy function, which will modify the deviation between evolution model of level set and Signed Distance Function (SDF) to reduce repeated initialization and improve convergence accuracy. Then, Gaussian pyramid energy term is incorporated into the energy function of geodesic active contour model to further accelerate its convergence speed. Finally, iteratively calculate the energy function of the proposed level set model to realize the evolution of contour curve, which can realize fast robust segmentation of complex image by solving the zero level set of the energy function. The comparative experiments between conventional method and the method proposed in this paper prove that the proposed method has higher processing speed than traditional C-V model on condition that the segmentation precision is guaranteed.

Active Contour (AC) is an algorithm widely used in segmentation for developing Computer-Aided Diagnosis (CAD) systems in ultrasound imaging. Existing AC models still retain an interactive nature. This is due to the large number of parameters and coefficients that require manual tuning to achieve stability. Which can result in human error and various issues caused by the inhomogeneity of ultrasound images, such as leakage, false areas, and local minima. In this study, an automatic object segmentation method was developed to assist radiologists in an efficient diagnosis process. The proposed method is called Automatic Combinatorial Active Contour (ACAC), which combines the simplification of the global region-based CV (Chan-Vese) model and improved-GAC (Geodesic Active Contour) for local segmentation. The results of testing with 50 datasets showed an accuracy value of 98.83%, precision of 95.26%, sensitivity of 86.58%, specificity of 99.63%, similarity of 90.58%, and IoU (Intersection over Union) of 82.87%. These quantitative performance metrics demonstrate that the ACAC method is suitable for implementation in a more efficient and accurate CAD system.

The rapid and accurate acquisition of water body information is of great significance to water resource investigation, flood disaster monitoring, ecological environment protection, and other fields. In this paper, the water boundary is optimized and extracted from single-polarization SAR images based on an improved geodesic active contour model (IMGAC). Firstly, the rough extraction results of the water body were obtained according to the adaptive threshold, and then a narrowband model was established, and the signed pressure force (SPF) function was introduced into the geodesic active contour (GAC) model. Finally, the optimal water boundary was obtained through continuous iteration. Compared with the active contour (AC) model without edge and the traditional GAC model, the results show that the IMGAC model proposed in this paper can reduce the calculation efficiency and improve the accuracy of water boundary detection. The F-measure index was used to evaluate the extraction accuracy of the three methods. IMGAC method had the highest extraction accuracy, which was 96.43%. The kappa coefficient reached 0.929. The F-measure index was 96.20%. Our study can provide a reference for water extraction and water boundary optimization.

Lumen segmentation of the carotid artery is an important preprocessing step with clinical application, because it facilitates subsequent analysis, including stenosis grading, the detection and quantification of plaque components in the vessel wall. But it is a challenging task owing to the low and varying contrast between the surrounding tissues. Plus, intensity inhomogeneity often occurs in medical images from different modalities, which causes undesirable side effects when the traditional Chan-Vese (CV) model is applied. In order to overcome the intensity inhomogeneity problem we improve the CV model by adding a local fitting term, which incorporates both local information and global information. We also introduce a penalizing energy to avoid the time-consuming re-initialization procedure in traditional level set method.We propose and validate a semi-automatic method for lumen segmentation of carotid artery in computed tomography angiography(CTA). First we manually select a seedpoint on the lumen area, then the segmentation is automatically obtained using a level set. By combining both global and local statistical information, we manage to overcome the inhomogeneous intensity distribution in the CTA images and provide more satisfying segmentation result than CV model. Experiments on carotid artery CTA data have demonstrated the efficiency and accuracy of our model, in addition our model is also less sensitive to the location of the initial contour. Therefore our method has the potential to replace the manual procedure of lumen segmentation in CTA, which is of great value for doctors with clinical applications.

For improving the accuracy and efficiency of image segmentation, an improved CV (Chan-Vese) model based on exponential kernel function is proposed. Firstly, according to the fast convergence character of exponential function, the efficiency is improved. Then the accuracy is more precise by modifying the energy function of the CV model. Finally, introducing level set function avoids the re-initialization and reduces the re-initialization time. Compared with the CV model, the CV model based on exponential kernel function has higher segmentation accuracy and stronger anti-noise ability, and needs less iteration times and running time.

Image segmentation is one of the crucial tasks in medical image processing and computer vision. The goal for image segmentation is to separate the pixels in the image into its constituent parts. Variational model in image segmentation involves formulating image segmentation as an optimization problem. The models seeking a partition of the image into meaningful regions by minimizing or maximizing an energy functional. These models often use geometric information to represent object boundaries. The models involve techniques such as active contours and level set methods. In this paper, the generalized mean model for image segmentation is investigated and modified. The model is a 2D region-based model which utilizes the fuzzy level set method. The model is compared with the active contour without edges model also known as the Chan-Vese for three types of images: without noise, with noise and with sinusoidal intensity inhomogeneity. Based on the numerical results, the generalized mean model obtained higher accuracy, Dice similarity measure, Jaccard and Kappa Index, comparedto the Chan-Vese model based on the tested images.The model is useful in medical imaging for disease detection, diagnosis, and treatment planning.

In remote sensing image analyses, the extraction of lake water bodies has been emphasized owing to its pivotal role in interpreting aquatic ecosystems, assessing hydrological trends, and detecting environmental changes. Although deep-learning-based techniques have been effectively deployed for this task, several challenges persist, including mis-segmentation of low-contrast regions, insufficient delineation of fuzzy boundaries, and over-segmentation in micro-regions. To address these issues, an innovative, end-to-end segmentation framework is proposed in this study. This framework ingeniously integrates the Geodesic Active Contour (GAC) model with the Vision Transformer (ViT) architecture, thereby offering a robust solution for fain-gained lake water body extraction. Specifically, the conventional GAC model is first revisited and reformulated. Subsequently, the Differentiable Spectral Clustering (DSC) module is designed for automatic contour initialization and lifts the dependence on hard threshold binarization. Finally, an iterative learning strategy is introduced to integrate the aforementioned models within the ViT architecture. This strategy serves to constrain the geometric characteristics, while also permitting dynamic adjustment of evolution parameters, facilitating enhanced refinement of spatial details and accuracy in segmentation results. Comprehensive experiments conducted on the newly constructed Global Lake View (GLV) dataset and a public benchmark demonstrated that the proposed method yields precise lake boundaries and achieves state-of-the-art performance.

Active contour models are always designed on the assumption that images are approximated by regions with piecewise-constant intensities. This assumption, however, cannot be satisfied when describing intensity inhomogeneous images which frequently occur in real world images and induced considerable difficulties in image segmentation. A milder assumption that the image is statistically homogeneous within different local regions may better suit real world images. By taking local image information into consideration, an enhanced active contour model is proposed to overcome difficulties caused by intensity inhomogeneity. In addition, according to curve evolution theory, only the region near contour boundaries is supposed to be evolved in each iteration. We try to detect the regions near contour boundaries adaptively for satisfying the requirement of curve evolution theory. In the proposed method, pixels within a selected region near contour boundaries have the opportunity to be updated in each iteration, which enables the contour to be evolved gradually. Experimental results on synthetic and real world images demonstrate the advantages of the proposed model when dealing with intensity inhomogeneity images.

To extract region of interests (ROI) in brain magnetic resonance imaging (MRI) with more than two objects and improve the segmentation accuracy, a hybrid model of a kernel-based fuzzy c-means(KFCM) clustering algorithm and Chan-Vese (CV) model for brain MRI segmentation is proposed. The approach consists of two successive stages. Firstly, the KFCM is used to make a coarse segmentation, which achieves the automatic selection of initial contour. Then an improved CV model is utilized to subdivide the image. Fuzzy membership degree from KFCM clustering is incorporated into the fidelity term of the 2-phase piecewise constant CV model to obtain accurate multi-object segmentation. Experimental results show that the proposed model has advantages both in accuracy and in robustness to noise in comparison with fuzzy c-means (FCM) clustering, KFCM, and the hybrid model of FCM and CV on brain MRI segmentation.