Vector Field Convolution Research Articles

A Novel Approach for Active Contour Initialization in 3D Medical Image Segmentation

Contour initialization is a big problem of the active contour model. Using the continuous features of the three-dimensional medical image, this paper proposes an initial contour prediction model. There are some changes in the boundary contours of the same object. We attribute these changes to continuous translation and similar deformation, and quantify into the centroid displacement and displacement of the point in the direction of Normal. The curve fitting method is used to predict the centroid displacement and the displacement of the points of the contours, which can provide more accurate prediction of changes in the contour. By predicting the initial contour, we have solved the contour initialization problem of the parametric active contour with external force using vector field convolution.

Harris function based active contour external force for image segmentation

Deformable active contour (snake) models are efficient tools for object boundary detection. Existing alterations of the traditional gradient vector flow (GVF) model have reduced sensitivity to noise, parameters and initial location, but high curvatures and noisy, weakly contrasted boundaries cause difficulties for them.This paper introduces two Harris based parametric snake models, Harris based gradient vector flow (HGVF) and Harris based vector field convolution (HVFC), which use the curvature-sensitive Harris matrix to achieve a balanced, twin-functionality (corner and edge) feature map. To avoid initial location sensitivity, starting contour is defined as the convex hull of the most attractive points of the map. In the experimental part we compared our methods to the traditional external energy-inspired state-of-the-art GVF and VFC; the recently published parametric decoupled active contour (DAC) and the non-parametric Chan–Vese (ACWE) techniques. Results show that our methods outperform the classical approaches, when tested on images with high curvature, noisy boundaries.

Brain volumetry: An active contour model-based segmentation followed by SVM-based classification

In this paper a novel automatic approach to identify brain structures in magnetic resonance imaging (MRI) is presented for volumetric measurements. The method is based on the idea of active contour models and support vector machine (SVM) classifiers. The main contributions of the presented method are effective modifications on brain images for active contour model and extracting simple and beneficial features for the SVM classifier. The segmentation process starts with a new generation of active contour models, i.e., vector field convolution (VFC) on modified brain images. VFC results are brain images with the least non-brain regions which are passed on to the SVM classification. The SVM features are selected according to the structure of brain tissues, gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF). SVM classifiers are trained for each brain tissue based on the set of extracted features. Although selected features are very simple, they are both sufficient and tissue separately effective. Our method validation is done using the gold standard brain MRI data set. Comparison of the results with the existing algorithms is a good indication of our approach's success.

A new active contour model based on the Conscience, Archiving and Mean-Movement mechanisms and the SOM

Active contour models are widely used in extracting object boundaries. However, most of these models usually fail to capture concave boundaries properly and impose high computational cost. In this paper, a new active contour model based on the Conscience, Archiving and Mean-Movement mechanisms and the SOM (CAMSOM) is proposed to eliminate these deficiencies. The proposed method extends the Batch SOM method (BSOM) by introducing three mechanisms of Conscience, Archiving and Mean-Movement mechanisms. To evaluate the performance of the proposed method compared with both energy minimization and SOM-based methods, some experiments are carried out on a set of grayscale images including synthetic and real ones. The experimental results are compared with those of the BSOM in terms of accuracy and convergence speed. The results reveal that, compared to BSOM, the proposed method requires less computations to converge to the object boundaries and extracts the boundaries of complex objects more accurately, even in the presence of weak or broken edges. Moreover, CAMSOM has higher performance and accuracy in capturing the boundaries of the objects placed arbitrarily in a multi-object scene, whereas the performance of BSOM in multi-object scenes highly depends on the arrangement of the objects. Compared to the energy minimization methods, the proposed method can accurately and quickly converges to the concave boundaries, whereas gradient vector flow (GVF) and vector field convolution (VFC) which are two well-known energy minimization methods get stuck in local minima and cannot proceed to the end of the concavity.

Boundary Detection in Medical Images Using Edge Following Algorithm Based on Intensity Gradient and Texture Gradient Features

Finding the correct boundary in noisy images is still a difficult task. This paper introduces a new edge following technique for boundary detection in noisy images. Utilization of the proposed technique is exhibited via its application to various types of medical images. Our proposed technique can detect the boundaries of objects in noisy images using the information from the intensity gradient via the vector image model and the texture gradient via the edge map. The performance and robustness of the technique have been tested to segment objects in synthetic noisy images and medical images including prostates in ultrasound images, left ventricles in cardiac magnetic resonance (MR) images, aortas in cardiovascular MR images, and knee joints in computerized tomography images. We compare the proposed segmentation technique with the active contour models (ACM), geodesic active contour models, active contours without edges, gradient vector flow snake models, and ACMs based on vector field convolution, by using the skilled doctors' opinions as the ground truths. The results show that our technique performs very well and yields better performance than the classical contour models. The proposed method is robust and applicable on various kinds of noisy images without prior knowledge of noise properties.

Hyperspectral boundary detection based on the Busyness Multiple Correlation Edge Detector and Alternating Vector Field Convolution snakes

Active contours, or snakes, are broadly used to detect linear features such as edges. However, they are often restricted in the delineation of regions of interest within the hyperspectral domain. In this paper, a new approach is presented, referred to as “Busyness Multiple Correlation Edge Detector”, that enables hyperspectral boundary detection using active contours such as “Alternating Vector Field Convolution” snakes. The combination of “Alternating Vector Field Convolution” snakes with the “Busyness Multiple Correlation Edge Detector” opens a broad set of applications by concurrent high convergence quality and speed. Furthermore, specific snake initialisations are tested. A series of examples are used to both demonstrate the approach and underline the benefits of the new methods.

Active Contour External Force Using Vector Field Convolution for Image Segmentation

Snakes, or active contours, have been widely used in image processing applications. Typical roadblocks to consistent performance include limited capture range, noise sensitivity, and poor convergence to concavities. This paper proposes a new external force for active contours, called vector field convolution (VFC), to address these problems. VFC is calculated by convolving the edge map generated from the image with the user-defined vector field kernel. We propose two structures for the magnitude function of the vector field kernel, and we provide an analytical method to estimate the parameter of the magnitude function. Mixed VFC is introduced to alleviate the possible leakage problem caused by choosing inappropriate parameters. We also demonstrate that the standard external force and the gradient vector flow (GVF) external force are special cases of VFC in certain scenarios. Examples and comparisons with GVF are presented in this paper to show the advantages of this innovation, including superior noise robustness, reduced computational cost, and the flexibility of tailoring the force field.