Level set method for image segmentation based on moment competition

Abstract

We propose a level set method for image segmentation which introduces the moment competition and weakly supervised information into the energy functional construction. Different from the region-based level set methods which use force competition, the moment competition is adopted to drive the contour evolution. Here, a so-called three-point labeling scheme is proposed to manually label three independent points (weakly supervised information) on the image. Then the intensity differences between the three points and the unlabeled pixels are used to construct the force arms for each image pixel. The corresponding force is generated from the global statistical information of a region-based method and weighted by the force arm. As a result, the moment can be constructed and incorporated into the energy functional to drive the evolving contour to approach the object boundary. In our method, the force arm can take full advantage of the three-point labeling scheme to constrain the moment competition. Additionally, the global statistical information and weakly supervised information are successfully integrated, which makes the proposed method more robust than traditional methods for initial contour placement and parameter setting. Experimental results with performance analysis also show the superiority of the proposed method on segmenting different types of complicated images, such as noisy images, threephase images, images with intensity inhomogeneity, and texture images.

Oriented distance regularized level set evolution for image segmentation

“…We used Equation ) to initialize the level set function with c 0 = 2, and performed the level set evolution with parameters μ = 0.1, λ = 3 and α = 1. The image was smoothed by G σ = 4 5 . Figure 10B shows the segmentation result in the DRLSE method after 700 iterations, the zero level contour converged to the outermost boundary 1 with no doubt.…”

“…The level set function was initialized by Equation ) with c 0 = 2 and evolved with parameters μ = 0.1, λ = 3 and α = 5. The original color image was first changed to a gray scale image, then smoothed with G σ = 3 5 . The gradient magnitude map of the smoothed image is shown in Figure 14B.…”

“…By minimizing an energy equation, the models can capture the target area of an image through a preset curve 1 . According to the form of the curve, the active contour models can be roughly categorized into two classes: the explicit active contour models 2,3 and the implicit active contour models 4,5 . The explicit active contours are constituted by parameterized point sets, which are hard to be set up and cannot handle the topological changes.…”

Segmentation of images by color features: A survey

“…Model-based methods involve active contour models and the level set methods [53,99,117,[171][172][173] . The central assumption of active contour model is to start with a curve around the object to be segmented, and gradually moves the curve toward its interior and stops on the true boundary of the object, the movement is controlled by using only low-level features such as discontinuity and homogeneity.…”

“…The final segmentation results are obtained by minimizing the final energy functional based on optimal evolution layer. In [53] the authors introduce the moment competition and weakly supervised information into the energy functional construction that is adopted to drive the contour evolution. The moment can be constructed and incorporated into the energy functional to drive the evolving contour to approach the object boundary.…”