Abstract
An adaptive regularized level set method for image segmentation is proposed. A weighted p(x)‐Dirichlet integral is presented as a geometric regularization on zero level curve, which is used to diminish the influence of image noise on level set evolution while ensuring the active contours not to pass through weak object boundaries. The idea behind the new energy integral is that the amount of regularization on the zero level curve can be adjusted automatically by the variable exponent p(x) to fit the image data. This energy is then incorporated into a level set formulation with an external energy term that drives the motion of the zero level set toward the desired objects boundaries, and a level set function regularization term that is necessary for maintaining stable level set evolution. The proposed model has been applied to a wide range of both real and synthetic images with promising results.
Highlights
Image segmentation is a key initial step before performing high-level tasks such as objects recognition and tracking 1, 2 in most computer vision applications
The weighted p x -Dirichlet integral integrating the gradient information is designed as a geometric regularization on zero level curve, which is used to diminish the influence of image noise on level set evolution while ensuring the active contours not to pass through weak object boundaries
The level set function φ x, y, t is initialized to φ0 x, y ρ nonzero constant ; we choose |ρ| 0.5 for all experiments
Summary
Image segmentation is a key initial step before performing high-level tasks such as objects recognition and tracking 1, 2 in most computer vision applications. Zhang et al 18 proposed a local image fitting LIF energy based on Gaussian filtering for variational level set to regularize the level set function. Wang et al 19 proposed a region-based tensor level set model for image segmentation, in which a three-order tensor involving the Gaussian filter bank was introduced to comprehensively depict features of pixels. The weighted p x -Dirichlet integral integrating the gradient information is designed as a geometric regularization on zero level curve, which is used to diminish the influence of image noise on level set evolution while ensuring the active contours not to pass through weak object boundaries.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have